PG2025 Conference Papers, Posters, and Demos

Permanent URI for this collection

Pacific Graphics 2025 - Pacific Graphics Conference Papers, Posters, and Demos
Taipei, Taiwan and hosted by National Chengchi University || October 14-17, 2025

(for Full Papers (CGF) see PG 2025 - CGF 44-7)
Character Animation
SMACC: Sketching Motion for Articulated Characters with Comics-based annotations
Amandine Legrand, Amal Dev Parakkat, and Damien Rohmer
B2F: End-to-End Body-to-Face Motion Generation with Style Reference
Bokyung Jang, Eunho Jung, and Yoonsang Lee
A Region-Based Facial Motion Analysis and Retargeting Model for 3D Characters
ChangAn Zhu, Sima Soltanpour, and Chris Joslin
Trajectory-guided Anime Video Synthesis via Effective Motion Learning
Jian Lin, Chengze Li, Haoyun Qin, Hanyuan Liu, Xueting Liu, Xin Ma, Cunjian Chen, and Tien-Tsin Wong
Digital Clothing
Hybrid Retrieval-Regression for Motion-Driven Loose-Fitting Garment Animation
Myeongjin Lee, Emmanuel Ian Libao, and Sung-Hee Lee
Frequency-Guided Self-Supervised Wind-Driven Garment Animation Simulation
Min Shi, Zhenyu Li, Tianlu Mao, Dengming Zhu, and Suqing Wang
Vehicle Dynamics and Interactions
Animating Vehicles Risk-Aware Interaction with Pedestrians Using Deep Reinforcement Learning
Hao-Ming Tsai and Sai-Keung Wong
Traffic Flow Reconstruction Using Two-Stage Optimization Based on Microscopic and Macroscopic Features
Jung-Hao Huang, Bo-Yun Lai, Sai-Keung Wong, and Wen-Chieh Lin
HiLo-Align: A Hierarchical Semantic Alignment Framework for Driving Decision Generation via Virtual-Physical Integration
Zehao Duan, Chengyan Huang, and Lin Wang
Animating Multi-Vehicle Interactions in Traffic Conflict Zones Using Operational Plans
Feng-Jui Chang, Sai-Keung Wong, Bo-Rui Huang, and Wen-Chieh Lin
Physical Simulation
DiffQN: Differentiable Quasi-Newton Method for Elastodynamics
Youshuai Cai, Chen Li, Haichuan Song, Youchen Xie, ChangBo Wang
PC-NCLaws: Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials
Xueguang Xie, Shu Yan, Shiwen Jia, Siyu Yang, Aimin Hao, Yang Gao, and Peng Yu
Parallel Constraint Graph Partitioning and Coloring for Realtime Soft-Body Cutting
Peng Yu, Ruiqi Wang, Chunlei Li, Yuxuan Li, Xiao Zhai, Yuanbo He, Hongyu Wu, Aimin Hao, and Yang Gao
Fast Multi-Body Coupling for Underwater Interactions
Tianhong Gao, Xuwen Chen, Xingqiao Li, Wei Li, Baoquan Chen, Zherong Pan, Kui Wu, and Mengyu Chu
An Adaptive Particle Fission-Fusion Approach for Dual-Particle SPH Fluid
Shusen Liu, Yuzhong Guo, Ying Qiao, and Xiaowei He
Detecting & Estimating from images
Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation
Kaiwen Ren, Lei Hu, Zhiheng Zhang, Yongjing Ye, and Shihong Xia
Skeletal Gesture Recognition Based on Joint Spatio-Temporal and Multi-Modal Learning
Zhijing Yu, Zhongjie Zhu, Di Ge, Renwei Tu, Yongqiang Bai, Yueping Yang, and Yuer Wang
Global-Local Complementary Representation Network for Vehicle Re-Identification
Mingchen Deng, Ziyao Tang, and Guoqiang Xiao
Breaking the Single-Stage Barrier: Synergistic Data-Model Adaptation at Test-Time for Medical Image Segmentation
Wenjuan Zhou, Wei Chen, Yulin He, Di Wu, and Chen Li
Enhancing Images
Region-Adaptive Low-Light Image Enhancement with Light Effect Suppression and Detail Preservation
Liheng Luo, Wantong Xie, Xiushan Xia, Zerui Li, and Yunbo Zhao
Image Reflection Separation via Adaptive Residual Correction and Feature Interaction Enhancement
Weijian Ke and Yijun Mo
ER-Diff: A Multi-Scale Exposure Residual-Guided Diffusion Model for Image Exposure Correction
TianZhen Chen, Jie Liu, and Yi Ru
Image Creation & Augmentation
Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
Haruo Fujiwara, Yusuke Mukuta, and Tatsuya Harada
Latent Interpretation for Diffusion Autoencoders via Integrated Semantic Reconstruction
Yixuan Ju, Xuan Tan, Zhenyang Zhu, Jiyi Li, and Xiaoyang Mao
Multi-Modality
PF-UCDR: A Local-Aware RGB-Phase Fusion Network with Adaptive Prompts for Universal Cross-Domain Retrieval
Yiqi Wu, Ronglei Hu, Huachao Wu, Fazhi He, and Dejun Zhang
KIN-FDNet:Dual-Branch KAN-INN Decomposition Network for Multi-Modality Image Fusion
Aimei Dong, Hao Meng, and Zhen Chen
Fabrication & Artistic designs
Neural Shadow Art
Caoliwen Wang, Bailin Deng, and Juyong Zhang
Reducing Visible Staircasing Artifacts Through Printing Orientation Using a Perception-Driven Metric
Mehmet Ata Yurtsever and Piotr Didyk
Point Clouds & Gaussian Splatting
GaussianMatch: Adaptive Learning Continuous Surfaces for Light Field Depth Estimation
Zexin Sun, Rongshan Chen, Yu Wang, Zhenglong Cui, Da Yang, Siyang Li, Xuefei Huang, and Hao Sheng
CGS: Continual Gaussian Splatting for Evolving 3D Scene Reconstruction
Shuojin Yang, Haoxiang Chen, and Taijiang Mu
Distance-Aware Tri-Perspective View for Efficient 3D Perception in Autonomous Driving
Yutao Tang, Jigang Zhao, Zhengrui Qin, Rui Qiu, Lingying Zhao, Jie Ren, and Guangxi Chen
GaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splatting
Feilong Du, Yalan Zhang, Yihang Ji, Xiaokun Wang, Chao Yao, Jiri Kosinka, Steffen Frey, Alexandru Telea, and Xiaojuan Ban
Shape Extraction or Editing
Unsupervised 3D Shape Parsing with Primitive Correspondence
Tianshu Zhao, Yanran Guan, and Oliver van Kaick
SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing
Jin Zhou, Hongliang Yang, Pengfei Xu, and Hui Huang
3D Reconstruction
VF-Plan: Bridging the Art Gallery Problem and Static LiDAR Scanning with Visibility Field Optimization
Biao Xiong, LongJun Zhang, Ruiqi Huang, Junwei Zhou, Syed Riaz un Nabi Jafri, Bojian Wu, and Fashuai Li
Generating 3D Hair Strips from Partial Strands using Diffusion Model
Gyeongmin Lee, Wonjong Jang, and Seungyong Lee
Attention-Guided Multi-scale Neural Dual Contouring
Fuli Wu, Chaoran Hu, Wenxuan Li, and Pengyi Hao
Lighting & Rendering
World-Space Direct and Indirect Lighting Sample Reuse with Persistent Reservoirs
JunPing Yuan, Chen Wang, Qi Sun, Jie Guo, Jia Bei, Yan Zhang, and Yanwen Guo
Iterative Lightmap Updates for Scene Editing
Guowei Lu, Christoph Peters, Petr Kellnhofer, and Elmar Eisemann
Stable Sample Caching for Interactive Stereoscopic Ray Tracing
Henrik Philippi, Henrik Wann Jensen, and Jeppe Revall Frisvad
Rendering & Inverse Rendering
Uni-IR: One Stage is Enough for Ambiguity-Reduced Inverse Rendering
Wenhang Ge, Jiawei Feng, Guibao Shen, and Ying-Cong Chen
By-Example Synthesis of Vector Textures
Christopher Palazzolo, Oliver van Kaick, and David Mould
Motion Vector-Based Frame Generation for Real-Time Rendering
Inwoo Ha, Young Chun Ahn, and Sung-eui Yoon
Interaction & Virtual Reality
CoSketcher: Collaborative and Iterative Sketch Generation with LLMs under Linguistic and Spatial Control
Liwen Mei, Manhao Guan, Yifan Zheng, and Dongliang Zhang
Easy Modeling of Man-Made Shapes in Virtual Reality
Haoyu Tang, Fancheng Gao, Kenny Tsu Wei Choo, Bernd Bickel, and Peng Song
ChromBrain Wall: A Virtual Reality Game Featuring Customized Full-Body Movement for Long-Term Physical and Cognitive Training in Older Adults
Hao Wu, Juanjuan Zhao, Aoyu Li, and Yan Qiang
Visualization
C2Views: Knowledge-based Colormap Design for Multiple-View Consistency
Yihan Hou, Yilin Ye, Liangwei Wang, Huamin Qu, and Wei Zeng
Structural Entropy Based Visualization of Social Networks
Mingliang Xue, Lu Chen, Chunyu Wei, Shuowei Hou, Lizhen Cui, Oliver Deussen, and Yunhai Wang
CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering
Qiangguo Jin, Xianyao Zheng, Hui Cui, Changming Sun, Yuqi Fang, Cong Cong, Ran Su, Leyi Wei, Ping Xuan, and Junbo Wang
Posters and Demos
Semi-supervised Dual-teacher Comparative Learning with Bidirectional Bisect Copy-paste for Medical Image Segmentation
Jiangxiong Fang, Shikuan Qi, Huaxiang Liu, Youyao Fu, and Shiqing Zhang
Self-Supervised Neural Global Illumination for Stereo-Rendering
Ziyang Zhang and Edgar Simo-Serra
3D Curve Development with Crossing and Twisting from 2D Drawings
Aurick Daniel Franciskus Setiadi, Jeng Wen Joshua Lean, Hao-Che Kao, and Shih-Hsuan Hung
SampleMono: Multi-Frame Spatiotemporal Extrapolation of 1-spp Path-Traced Sequences via Transfer Learning
Mehmet Oguz Derin
A Multimodal Dataset for Dialogue Intent Recognition through Human Movement and Nonverbal Cues
Shu-Wei Lin, Jia-Xiang Zhang, Jun-Fu Lin Lu, Yi-Jheng Huang, and Junpo Zhang
Body-Scale-Invariant Motion Embedding for Motion Similarity
Xian Du, Chuyan Quan, and Ri Yu
WotaBeats: Avatar-based Rhythm Interaction Applied Wotagei in Virtual Reality Experience
Kalin Guanlun Lai, Guan-Wen Wang, Yi Ting, Heng-Hao Wang, Hsuan-Tung Lai, Zhe-Cheng Chang, Po-Hung Chiang, and Tse-Yu Pan
From Steps to Verses: Following the Shared Journey of Language and the Body Through Wearable Technology
Huang Yi-Wen and Tsai Tsun-Hung
ServeSense: Interactive VR Tennis Serve Training System Enhanced with Haptic Feedback
Chi Tsao, Ryan Shan, Neng-Hao Yu, and Tse-Yu Pan
Exploring Perceptual Homogenization through a VR-Based AI Narrative
Bing-Chen Kao and Tsun-Hung Tsai
Avatar Animations and Audio Fillers for Managing Response Delays
Gopi Krishnan Singaravelan, Zhi Lynn Lay, and Ping-Hsuan Han

BibTeX (PG2025 Conference Papers, Posters, and Demos)
@inproceedings{
10.2312:pg.20252024,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Pacific Graphics 2025 - Conference Papers, Posters, and Demos: Frontmatter}},
author = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20252024}
}
@inproceedings{
10.2312:pg.20251255,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
SMACC: Sketching Motion for Articulated Characters with Comics-based annotations}},
author = {
Legrand, Amandine
and
Parakkat, Amal Dev
and
Rohmer, Damien
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251255}
}
@inproceedings{
10.2312:pg.20251256,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
B2F: End-to-End Body-to-Face Motion Generation with Style Reference}},
author = {
Jang, Bokyung
and
Jung, Eunho
and
Lee, Yoonsang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251256}
}
@inproceedings{
10.2312:pg.20251257,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
A Region-Based Facial Motion Analysis and Retargeting Model for 3D Characters}},
author = {
Zhu, ChangAn
and
Soltanpour, Sima
and
Joslin, Chris
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251257}
}
@inproceedings{
10.2312:pg.20251258,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Trajectory-guided Anime Video Synthesis via Effective Motion Learning}},
author = {
Lin, Jian
and
Li, Chengze
and
Qin, Haoyun
and
Liu, Hanyuan
and
Liu, Xueting
and
Ma, Xin
and
Chen, Cunjian
and
Wong, Tien-Tsin
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251258}
}
@inproceedings{
10.2312:pg.20251259,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Hybrid Retrieval-Regression for Motion-Driven Loose-Fitting Garment Animation}},
author = {
Lee, Myeongjin
and
Libao, Emmanuel Ian
and
Lee, Sung-Hee
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251259}
}
@inproceedings{
10.2312:pg.20251260,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Frequency-Guided Self-Supervised Wind-Driven Garment Animation Simulation}},
author = {
Shi, Min
and
Li, Zhenyu
and
Mao, Tianlu
and
Zhu, Dengming
and
Wang, Suqing
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251260}
}
@inproceedings{
10.2312:pg.20251261,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Animating Vehicles Risk-Aware Interaction with Pedestrians Using Deep Reinforcement Learning}},
author = {
Tsai, Hao-Ming
and
Wong, Sai-Keung
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251261}
}
@inproceedings{
10.2312:pg.20251262,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Traffic Flow Reconstruction Using Two-Stage Optimization Based on Microscopic and Macroscopic Features}},
author = {
Huang, Jung-Hao
and
Lai, Bo-Yun
and
Wong, Sai-Keung
and
Lin, Wen-Chieh
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251262}
}
@inproceedings{
10.2312:pg.20251263,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
HiLo-Align: A Hierarchical Semantic Alignment Framework for Driving Decision Generation via Virtual-Physical Integration}},
author = {
Duan, Zehao
and
Huang, Chengyan
and
Wang, Lin
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251263}
}
@inproceedings{
10.2312:pg.20251264,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Animating Multi-Vehicle Interactions in Traffic Conflict Zones Using Operational Plans}},
author = {
Chang, Feng-Jui
and
Wong, Sai-Keung
and
Huang, Bo-Rui
and
Lin, Wen-Chieh
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251264}
}
@inproceedings{
10.2312:pg.20251265,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
DiffQN: Differentiable Quasi-Newton Method for Elastodynamics}},
author = {
Cai, Youshuai
and
Li, Chen
and
Song, Haichuan
and
Xie, Youchen
and
Wang, ChangBo
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251265}
}
@inproceedings{
10.2312:pg.20251266,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
PC-NCLaws: Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials}},
author = {
Xie, Xueguang
and
Yan, Shu
and
Jia, Shiwen
and
Yang, Siyu
and
Hao, Aimin
and
Gao, Yang
and
Yu, Peng
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251266}
}
@inproceedings{
10.2312:pg.20251267,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Parallel Constraint Graph Partitioning and Coloring for Realtime Soft-Body Cutting}},
author = {
Yu, Peng
and
Wang, Ruiqi
and
Li, Chunlei
and
Li, Yuxuan
and
Zhai, Xiao
and
He, Yuanbo
and
Wu, Hongyu
and
Hao, Aimin
and
Gao, Yang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251267}
}
@inproceedings{
10.2312:pg.20251268,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Fast Multi-Body Coupling for Underwater Interactions}},
author = {
Gao, Tianhong
and
Chen, Xuwen
and
Li, Xingqiao
and
Li, Wei
and
Chen, Baoquan
and
Pan, Zherong
and
Wu, Kui
and
Chu, Mengyu
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251268}
}
@inproceedings{
10.2312:pg.20251269,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
An Adaptive Particle Fission-Fusion Approach for Dual-Particle SPH Fluid}},
author = {
Liu, Shusen
and
Guo, Yuzhong
and
Qiao, Ying
and
He, Xiaowei
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251269}
}
@inproceedings{
10.2312:pg.20251270,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation}},
author = {
Ren, Kaiwen
and
Hu, Lei
and
Zhang, Zhiheng
and
Ye, Yongjing
and
Xia, Shihong
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251270}
}
@inproceedings{
10.2312:pg.20251271,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Skeletal Gesture Recognition Based on Joint Spatio-Temporal and Multi-Modal Learning}},
author = {
Yu, Zhijing
and
Zhu, Zhongjie
and
Ge, Di
and
Tu, Renwei
and
Bai, Yongqiang
and
Yang, Yueping
and
Wang, Yuer
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251271}
}
@inproceedings{
10.2312:pg.20251272,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Global-Local Complementary Representation Network for Vehicle Re-Identification}},
author = {
Deng, Mingchen
and
Tang, Ziyao
and
Xiao, Guoqiang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251272}
}
@inproceedings{
10.2312:pg.20251273,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Breaking the Single-Stage Barrier: Synergistic Data-Model Adaptation at Test-Time for Medical Image Segmentation}},
author = {
Zhou, Wenjuan
and
Chen, Wei
and
He, Yulin
and
Wu, Di
and
Li, Chen
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251273}
}
@inproceedings{
10.2312:pg.20251274,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Region-Adaptive Low-Light Image Enhancement with Light Effect Suppression and Detail Preservation}},
author = {
Luo, Liheng
and
Xie, Wantong
and
Xia, Xiushan
and
Li, Zerui
and
Zhao, Yunbo
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251274}
}
@inproceedings{
10.2312:pg.20251275,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Image Reflection Separation via Adaptive Residual Correction and Feature Interaction Enhancement}},
author = {
Ke, Weijian
and
Mo, Yijun
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251275}
}
@inproceedings{
10.2312:pg.20251276,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
ER-Diff: A Multi-Scale Exposure Residual-Guided Diffusion Model for Image Exposure Correction}},
author = {
Chen, TianZhen
and
Liu, Jie
and
Ru, Yi
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251276}
}
@inproceedings{
10.2312:pg.20251277,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control}},
author = {
Fujiwara, Haruo
and
Mukuta, Yusuke
and
Harada, Tatsuya
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251277}
}
@inproceedings{
10.2312:pg.20251278,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Latent Interpretation for Diffusion Autoencoders via Integrated Semantic Reconstruction}},
author = {
Ju, Yixuan
and
Tan, Xuan
and
Zhu, Zhenyang
and
Li, Jiyi
and
Mao, Xiaoyang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251278}
}
@inproceedings{
10.2312:pg.20251279,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
PF-UCDR: A Local-Aware RGB-Phase Fusion Network with Adaptive Prompts for Universal Cross-Domain Retrieval}},
author = {
Wu, Yiqi
and
Hu, Ronglei
and
Wu, Huachao
and
He, Fazhi
and
Zhang, Dejun
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251279}
}
@inproceedings{
10.2312:pg.20251280,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
KIN-FDNet:Dual-Branch KAN-INN Decomposition Network for Multi-Modality Image Fusion}},
author = {
Dong, Aimei
and
Meng, Hao
and
Chen, Zhen
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251280}
}
@inproceedings{
10.2312:pg.20251281,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Neural Shadow Art}},
author = {
Wang, Caoliwen
and
Deng, Bailin
and
Zhang, Juyong
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251281}
}
@inproceedings{
10.2312:pg.20251282,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Reducing Visible Staircasing Artifacts Through Printing Orientation Using a Perception-Driven Metric}},
author = {
Yurtsever, Mehmet Ata
and
Didyk, Piotr
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251282}
}
@inproceedings{
10.2312:pg.20251283,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
GaussianMatch: Adaptive Learning Continuous Surfaces for Light Field Depth Estimation}},
author = {
Sun, Zexin
and
Chen, Rongshan
and
Wang, Yu
and
Cui, Zhenglong
and
Yang, Da
and
Li, Siyang
and
Huang, Xuefei
and
Sheng, Hao
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251283}
}
@inproceedings{
10.2312:pg.20251284,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
CGS: Continual Gaussian Splatting for Evolving 3D Scene Reconstruction}},
author = {
Yang, Shuojin
and
Chen, Haoxiang
and
Mu, Taijiang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251284}
}
@inproceedings{
10.2312:pg.20251285,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Distance-Aware Tri-Perspective View for Efficient 3D Perception in Autonomous Driving}},
author = {
Tang, Yutao
and
Zhao, Jigang
and
Qin, Zhengrui
and
Qiu, Rui
and
Zhao, Lingying
and
Ren, Jie
and
Chen, Guangxi
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251285}
}
@inproceedings{
10.2312:pg.20251286,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
GaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splatting}},
author = {
Du, Feilong
and
Zhang, Yalan
and
Ji, Yihang
and
Wang, Xiaokun
and
Yao, Chao
and
Kosinka, Jiri
and
Frey, Steffen
and
Telea, Alexandru
and
Ban, Xiaojuan
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251286}
}
@inproceedings{
10.2312:pg.20251287,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Unsupervised 3D Shape Parsing with Primitive Correspondence}},
author = {
Zhao, Tianshu
and
Guan, Yanran
and
Kaick, Oliver van
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251287}
}
@inproceedings{
10.2312:pg.20251288,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing}},
author = {
Zhou, Jin
and
Yang, Hongliang
and
Xu, Pengfei
and
Huang, Hui
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251288}
}
@inproceedings{
10.2312:pg.20251289,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
VF-Plan: Bridging the Art Gallery Problem and Static LiDAR Scanning with Visibility Field Optimization}},
author = {
Xiong, Biao
and
Zhang, LongJun
and
Huang, Ruiqi
and
Zhou, Junwei
and
Jafri, Syed Riaz un Nabi
and
Wu, Bojian
and
Li, Fashuai
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251289}
}
@inproceedings{
10.2312:pg.20251290,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Generating 3D Hair Strips from Partial Strands using Diffusion Model}},
author = {
Lee, Gyeongmin
and
Jang, Wonjong
and
Lee, Seungyong
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251290}
}
@inproceedings{
10.2312:pg.20251291,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Attention-Guided Multi-scale Neural Dual Contouring}},
author = {
Wu, Fuli
and
Hu, Chaoran
and
Li, Wenxuan
and
Hao, Pengyi
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251291}
}
@inproceedings{
10.2312:pg.20251292,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
World-Space Direct and Indirect Lighting Sample Reuse with Persistent Reservoirs}},
author = {
Yuan, JunPing
and
Wang, Chen
and
Sun, Qi
and
Guo, Jie
and
Bei, Jia
and
Zhang, Yan
and
Guo, Yanwen
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251292}
}
@inproceedings{
10.2312:pg.20251293,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Iterative Lightmap Updates for Scene Editing}},
author = {
Lu, Guowei
and
Peters, Christoph
and
Kellnhofer, Petr
and
Eisemann, Elmar
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251293}
}
@inproceedings{
10.2312:pg.20251294,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Stable Sample Caching for Interactive Stereoscopic Ray Tracing}},
author = {
Philippi, Henrik
and
Jensen, Henrik Wann
and
Frisvad, Jeppe Revall
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251294}
}
@inproceedings{
10.2312:pg.20251295,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Uni-IR: One Stage is Enough for Ambiguity-Reduced Inverse Rendering}},
author = {
Ge, Wenhang
and
Feng, Jiawei
and
Shen, Guibao
and
Chen, Ying-Cong
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251295}
}
@inproceedings{
10.2312:pg.20251296,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
By-Example Synthesis of Vector Textures}},
author = {
Palazzolo, Christopher
and
Kaick, Oliver van
and
Mould, David
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251296}
}
@inproceedings{
10.2312:pg.20251297,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Motion Vector-Based Frame Generation for Real-Time Rendering}},
author = {
Ha, Inwoo
and
Ahn, Young Chun
and
Yoon, Sung-eui
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251297}
}
@inproceedings{
10.2312:pg.20251298,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
CoSketcher: Collaborative and Iterative Sketch Generation with LLMs under Linguistic and Spatial Control}},
author = {
Mei, Liwen
and
Guan, Manhao
and
Zheng, Yifan
and
Zhang, Dongliang
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251298}
}
@inproceedings{
10.2312:pg.20251299,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Easy Modeling of Man-Made Shapes in Virtual Reality}},
author = {
Tang, Haoyu
and
Gao, Fancheng
and
Choo, Kenny Tsu Wei
and
Bickel, Bernd
and
Song, Peng
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251299}
}
@inproceedings{
10.2312:pg.20251300,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
ChromBrain Wall: A Virtual Reality Game Featuring Customized Full-Body Movement for Long-Term Physical and Cognitive Training in Older Adults}},
author = {
Wu, Hao
and
Zhao, Juanjuan
and
Li, Aoyu
and
Qiang, Yan
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251300}
}
@inproceedings{
10.2312:pg.20251301,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
C2Views: Knowledge-based Colormap Design for Multiple-View Consistency}},
author = {
Hou, Yihan
and
Ye, Yilin
and
Wang, Liangwei
and
Qu, Huamin
and
Zeng, Wei
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251301}
}
@inproceedings{
10.2312:pg.20251302,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Structural Entropy Based Visualization of Social Networks}},
author = {
Xue, Mingliang
and
Chen, Lu
and
Wei, Chunyu
and
Hou, Shuowei
and
Cui, Lizhen
and
Deussen, Oliver
and
Wang, Yunhai
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251302}
}
@inproceedings{
10.2312:pg.20251303,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering}},
author = {
Jin, Qiangguo
and
Zheng, Xianyao
and
Cui, Hui
and
Sun, Changming
and
Fang, Yuqi
and
Cong, Cong
and
Su, Ran
and
Wei, Leyi
and
Xuan, Ping
and
Wang, Junbo
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251303}
}
@inproceedings{
10.2312:pg.20251304,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Semi-supervised Dual-teacher Comparative Learning with Bidirectional Bisect Copy-paste for Medical Image Segmentation}},
author = {
Fang, Jiangxiong
and
Qi, Shikuan
and
Liu, Huaxiang
and
Fu, Youyao
and
Zhang, Shiqing
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251304}
}
@inproceedings{
10.2312:pg.20251305,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Self-Supervised Neural Global Illumination for Stereo-Rendering}},
author = {
Zhang, Ziyang
and
Simo-Serra, Edgar
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251305}
}
@inproceedings{
10.2312:pg.20251306,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
3D Curve Development with Crossing and Twisting from 2D Drawings}},
author = {
Setiadi, Aurick Daniel Franciskus
and
Lean, Jeng Wen Joshua
and
Kao, Hao-Che
and
Hung, Shih-Hsuan
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251306}
}
@inproceedings{
10.2312:pg.20251307,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
SampleMono: Multi-Frame Spatiotemporal Extrapolation of 1-spp Path-Traced Sequences via Transfer Learning}},
author = {
Derin, Mehmet Oguz
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251307}
}
@inproceedings{
10.2312:pg.20251310,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
A Multimodal Dataset for Dialogue Intent Recognition through Human Movement and Nonverbal Cues}},
author = {
Lin, Shu-Wei
and
Zhang, Jia-Xiang
and
Lu, Jun-Fu Lin
and
Huang, Yi-Jheng
and
Zhang, Junpo
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251310}
}
@inproceedings{
10.2312:pg.20251311,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Body-Scale-Invariant Motion Embedding for Motion Similarity}},
author = {
Du, Xian
and
Quan, Chuyan
and
Yu, Ri
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251311}
}
@inproceedings{
10.2312:pg.20251312,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
WotaBeats: Avatar-based Rhythm Interaction Applied Wotagei in Virtual Reality Experience}},
author = {
Lai, Kalin Guanlun
and
Wang, Guan-Wen
and
Ting, Yi
and
Wang, Heng-Hao
and
Lai, Hsuan-Tung
and
Chang, Zhe-Cheng
and
Chiang, Po-Hung
and
Pan, Tse-Yu
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251312}
}
@inproceedings{
10.2312:pg.20251313,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
From Steps to Verses: Following the Shared Journey of Language and the Body Through Wearable Technology}},
author = {
Yi-Wen, Huang
and
Tsun-Hung, Tsai
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251313}
}
@inproceedings{
10.2312:pg.20251314,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
ServeSense: Interactive VR Tennis Serve Training System Enhanced with Haptic Feedback}},
author = {
Tsao, Chi
and
Shan, Ryan
and
Yu, Neng-Hao
and
Pan, Tse-Yu
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251314}
}
@inproceedings{
10.2312:pg.20251315,
booktitle = {
Pacific Graphics Conference Papers, Posters, and Demos},
editor = {
Christie, Marc
and
Han, Ping-Hsuan
and
Lin, Shih-Syun
and
Pietroni, Nico
and
Schneider, Teseo
and
Tsai, Hsin-Ruey
and
Wang, Yu-Shuen
and
Zhang, Eugene
}, title = {{
Exploring Perceptual Homogenization through a VR-Based AI Narrative}},
author = {
Kao, Bing-Chen
and
Tsai, Tsun-Hung
}, year = {
2025},
publisher = {
The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {
10.2312/pg.20251315}
}

Browse

Recent Submissions

Now showing 1 - 60 of 61
  • Item
    Pacific Graphics 2025 - Conference Papers, Posters, and Demos: Frontmatter
    (The Eurographics Association, 2025) Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
  • Item
    SMACC: Sketching Motion for Articulated Characters with Comics-based annotations
    (The Eurographics Association, 2025) Legrand, Amandine; Parakkat, Amal Dev; Rohmer, Damien; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We introduce SMACC, a sketch-based system for animating short sequences of 3D articulated characters inspired by 2D comic motion line annotations. SMACC relies on classical rules of motion depiction used in comic books, allowing the depiction of dynamism in static images while being universally understood. Building on this, SMACC introduces an algorithmic interpretation of these principles in the context of a 3D character animation, guided by three fundamental types of motion lines: trajectory, circumfixing and impact. The adaptation to rigged 3D characters relies on the automatic computation of how these motion cues spatially influence the character's skeleton, achieved through a global analysis of sketch annotations relative to the character's pose. The resulting animation is generated by encoding the kinematic clues and constraints into joint angular velocities. Finally, the proof-of-concept demonstrated by SMACC is validated through a user study, which evaluates the effectiveness and accuracy of this sketch-based approach applied to 3D character animation.
  • Item
    B2F: End-to-End Body-to-Face Motion Generation with Style Reference
    (The Eurographics Association, 2025) Jang, Bokyung; Jung, Eunho; Lee, Yoonsang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Human motion naturally integrates body movements and facial expressions, forming a unified perception. If a virtual character's facial expression does not align well with its body movements, it may weaken the perception of the character as a cohesive whole. Motivated by this, we propose B2F, a model that generates facial motions aligned with body movements. B2F takes a facial style reference as input, generating facial animations that reflect the provided style while maintaining consistency with the associated body motion. To achieve this, B2F learns a disentangled representation of content and style, using alignment and consistency-based objectives. We represent style using discrete latent codes learned via the Gumbel-Softmax trick, enabling diverse expression generation with a structured latent representation. B2F outputs facial motion in the FLAME format, making it compatible with SMPL-X characters, and supports ARKit-style avatars through a dedicated conversion module. Our evaluations show that B2F generates expressive and engaging facial animations that synchronize with body movements and style intent, while mitigating perceptual dissonance from mismatched cues, and generalizing across diverse characters and styles.
  • Item
    A Region-Based Facial Motion Analysis and Retargeting Model for 3D Characters
    (The Eurographics Association, 2025) Zhu, ChangAn; Soltanpour, Sima; Joslin, Chris; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    With the expanding applicable scenarios of 3D facial animation, abundant research has been done on facial motion capture, 3D face parameterization, and retargeting. However, current retargeting methods still struggle to reflect the source motion on a target 3D face accurately. One major reason is that the source motion is not translated into precise representations of the motion meanings and intensities, resulting in the target 3D face presenting inaccurate motion semantics. We propose a region-based facial motion analysis and retargeting model that focuses on predicting detailed facial motion representations and providing a plausible retargeting result through 3D facial landmark input. We have defined the regions based on facial muscle behaviours and trained a motion-to-representation regression for each region. A refinement process, designed using an autoencoder and a motion predictor for facial landmarks, which works for both real-life subjects' and fictional characters' face rigs, is also introduced to improve the precision of the retargeting. The region-based strategy effectively balances the motion scales of the different facial regions, providing reliable representation prediction and retargeting results. The representation prediction and refinement with 3D facial landmark input have enabled flexible application scenarios such as video-based and marker-based motion retargeting, and the reuse of animation assets for Computer-Generated (CG) characters. Our evaluation shows that the proposed model provides semantically more accurate and visually more natural results than similar methods and the commercial solution from Faceware. Our ablation study demonstrates the positive effects of the region-based strategy and the refinement process.
  • Item
    Trajectory-guided Anime Video Synthesis via Effective Motion Learning
    (The Eurographics Association, 2025) Lin, Jian; Li, Chengze; Qin, Haoyun; Liu, Hanyuan; Liu, Xueting; Ma, Xin; Chen, Cunjian; Wong, Tien-Tsin; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Cartoon and anime motion production is traditionally labor-intensive, requiring detailed animatics and extensive inbetweening from keyframes. To streamline this process, we propose a novel framework that synthesizes motion directly from a single colored keyframe, guided by user-provided trajectories. Addressing the limitations of prior methods, which struggle with anime due to reliance on optical flow estimators and models trained on natural videos, we introduce an efficient motion representation specifically adapted for anime, leveraging CoTracker to capture sparse frame-to-frame tracking effectively. To achieve our objective, we design a two-stage learning mechanism: the first stage predicts sparse motion from input frames and trajectories, generating a motion preview sequence via explicit warping; the second stage refines these previews into high-quality anime frames by fine-tuning ToonCrafter, an anime-specific video diffusion model. We train our framework on a novel animation video dataset comprising more than 500,000 clips. Experimental results demonstrate significant improvements in animating still frames, achieving better alignment with user-provided trajectories and more natural motion patterns while preserving anime stylization and visual quality. Our method also supports versatile applications, including motion manga generation and 2D vector graphic animations. The data and code will be released upon acceptance. For models, datasets and additional visual comparisons and ablation studies, visit our project page: https://animemotiontraj.github.io/.
  • Item
    Hybrid Retrieval-Regression for Motion-Driven Loose-Fitting Garment Animation
    (The Eurographics Association, 2025) Lee, Myeongjin; Libao, Emmanuel Ian; Lee, Sung-Hee; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We present a hybrid retrieval-regression framework for motion-driven garment animation leveraging a shared discrete codebook. Our method targets the challenge of animating loose-fitting garments, whose dynamic behaviors exhibit high variability and less direct correlation with body motion-making them difficult to handle with conventional example-based approaches that assume tightly coupled motion-garment relationships. To address this, we project both motion and garment animation clips into a shared discrete codebook via Gumbel-Softmax-based quantization, allowing them to be aligned in a semantically consistent space where cross-retrieval can be performed using simple distance metrics. During inference, we adaptively switch between retrieval and regression based on the confidence derived from the codebook probability distribution, allowing the system to remain robust in the presence of ambiguous or unseen motions. We leverage a pre-trained mesh autoencoder to obtain garment latents that preserve local geometric structure, enabling smoother transitions and more geometrically consistent interpolation between retrieved and regressed animation segments efficiently. Experimental results demonstrate that our approach improves the accuracy and plausibility of garment animation for complex garments under diverse motion inputs, while maintaining robustness to unseen scenarios and achieving low simulation error for high-quality garment animation.
  • Item
    Frequency-Guided Self-Supervised Wind-Driven Garment Animation Simulation
    (The Eurographics Association, 2025) Shi, Min; Li, Zhenyu; Mao, Tianlu; Zhu, Dengming; Wang, Suqing; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Realistic simulation of garment deformation under coupled multi-physical fields remains a critical challenge in 3d animation, due to diverse properties of fabric and complex interactions with external forces. Existing methods mainly focus on humandriven garment animation and offer dynamic environmental factors such as wind fields. Moreover, supervised learning methods suffer from strong data dependency and limited generalization. We propose FWGNet, a self-supervised training framework based on graph neural networks (GNNs) that models the physical interaction between garments, the human body and wind as an unified physical system. The framework is trained using differentiable physics-based constraints. A core component of FWGNet is a wind feature encoder that utilizes wavelet transforms to project wind velocity sequences into the frequency domain, enabling the network to effectively capture multi-scale turbulence effects on fabric behavior. To eliminate dependence on large datasets, we introduce physics-informed loss functions that incorporate gravitational potential energy, aerodynamic wind forces, and fabric deformation constraints. Experiments demonstrate that our approach produces highly realistic visual effects, such as detailed wrinkle formation and fabric fluttering under dynamic wind conditions. Quantitative evaluations across physical metrics confirm that FWGNet achieves a strong balance between physical accuracy and visual realism, particularly in complex scenarios involving coupled physical interactions.
  • Item
    Animating Vehicles Risk-Aware Interaction with Pedestrians Using Deep Reinforcement Learning
    (The Eurographics Association, 2025) Tsai, Hao-Ming; Wong, Sai-Keung; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper introduces a deep reinforcement learning-based system for ego vehicle control, enabling interaction with dynamic objects like pedestrians and animals. These objects display varied crossing behaviors, including sudden stops and directional shifts. The system uses a perception module to identify road structures, key pedestrians, inner wheel difference zones, and object movements. This allows the vehicle to make context-aware decisions, such as yielding, turning, or maintaining speed. The training process includes reward terms for speed, time, time-to-collision, and cornering to refine policy learning. Experiments show ego vehicles can adjust their behavior, such as decelerating or yielding, to avoid collisions. Ablation studies highlighted the importance of specific reward terms and state components. Animation results show that ego vehicles could safely interact with pedestrians or animals that exhibited sudden acceleration, mid-crossing directional changes, and abrupt stops.
  • Item
    Traffic Flow Reconstruction Using Two-Stage Optimization Based on Microscopic and Macroscopic Features
    (The Eurographics Association, 2025) Huang, Jung-Hao; Lai, Bo-Yun; Wong, Sai-Keung; Lin, Wen-Chieh; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper presents a two-stage optimization method for traffic reconstruction that considers both microscopic and macroscopic features. The method employs a microscopic driving model and uses the average speeds in the lanes as a macroscopic metric to reconstruct traffic that balances the characteristics of traffic flow and vehicle behaviors. Our results on the NGSIM dataset, conducted primarily on straight road segments, demonstrate that the proposed method effectively balances the preservation of microscopic-level details with the simulation of macroscopic traffic flows. Both stages of our method outperform previous work in their respective domains. Furthermore, animated results rendered in the CARLA simulator highlight the realism of the generated driving behaviors, underscoring the model's ability to accurately reproduce various scenarios observed in real-world traffic. By recovering physical simulation parameters from real data, our framework can be utilized to generate diverse, realistic traffic flows, supporting applications such as traffic animation, data augmentation, system testing, and traffic behavior analysis.
  • Item
    HiLo-Align: A Hierarchical Semantic Alignment Framework for Driving Decision Generation via Virtual-Physical Integration
    (The Eurographics Association, 2025) Duan, Zehao; Huang, Chengyan; Wang, Lin; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Autonomous vehicles operating in uncertain urban environments are required to reason over complex multi-agent interactions while adhering to stringent safety requirements. Hierarchical frameworks often use large models for high-level (virtual-layer) planning and deep reinforcement learning for low-level (physical-layer) control. However, semantic and temporal misalignment between layers leads to command errors and delayed response. We propose HiLo-Align, a hybrid hierarchical framework that unifies both layers via a shared semantic space and time scale. By explicitly modeling cross-layer alignment, HiLo-Align improves control coordination and semantic consistency. Experimental results on both simulation and real-world datasets indicate enhanced collision avoidance, generalization, and robustness in high-risk urban environments.
  • Item
    Animating Multi-Vehicle Interactions in Traffic Conflict Zones Using Operational Plans
    (The Eurographics Association, 2025) Chang, Feng-Jui; Wong, Sai-Keung; Huang, Bo-Rui; Lin, Wen-Chieh; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper introduces an agent-based method for generating animations of intricate vehicle interactions by regulating behaviors in conflict zones on non-signalized road segments. As vehicles move along their paths, they create sweeping regions representing the areas they may occupy. The method assigns operation plans to vehicles, regulating their crossing and yielding strategies within intersecting or merging conflict zones. This approach enables various vehicle interactions, combining basic actions such as acceleration, deceleration, keeping speed, and stopping. Experimental results demonstrate that our method generates plausible interaction behaviors in diverse road structures, including intersections, Y-junctions, and midblocks. This method could be beneficial for applications in traffic scenario planning, self-driving vehicles, driving training, and education.
  • Item
    DiffQN: Differentiable Quasi-Newton Method for Elastodynamics
    (The Eurographics Association, 2025) Cai, Youshuai; Li, Chen; Song, Haichuan; Xie, Youchen; Wang, ChangBo; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We propose DiffQN, an efficient differentiable quasi-Newton method for elastodynamics simulation, addressing the challenges of high computational cost and limited material generality in existing differentiable physics frameworks. Our approach employs a per-frame initial Hessian approximation and selectively delays Hessian updates, resulting in improved convergence and faster forward simulation compared to prior methods such as DiffPD. During backpropagation, we further reduce gradient evaluation costs by reusing prefactorized linear system solvers from the forward pass. Unlike previous approaches, our method supports a wide range of hyperelastic materials without restrictions on material energy functions, enabling the simulation of more general physical phenomena. To efficiently handle high-resolution systems with large degrees of freedom, we introduce a subspace optimization strategy that projects both forward simulation and backpropagation into a low-dimensional subspace, significantly improving computational and memory efficiency. Our subspace method can provide effective initial guesses for subsequent full-space optimization. We validate our framework on diverse applications, including system identification, initial state optimization, and facial animation, demonstrating robust performance and achieving up to 1.8× to 18.9× speedup over state-of-the-art methods.
  • Item
    PC-NCLaws: Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials
    (The Eurographics Association, 2025) Xie, Xueguang; Yan, Shu; Jia, Shiwen; Yang, Siyu; Hao, Aimin; Gao, Yang; Yu, Peng; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    While data-driven methods offer significant promise for modeling complex materials, they often face challenges in generalizing across diverse physical scenarios and maintaining physical consistency. To address these limitations, we propose a generalizable framework called Physics-Embedded Conditional Neural Constitutive Laws for Elastoplastic Materials, which combines the partial differential equations with neural networks. Specifically, the model employs two separate neural networks to model elastic and plastic constitutive laws. Simultaneously, the model incorporates physical parameters as conditional inputs and is trained on comprehensive datasets encompassing multiple scenarios with varying physical parameters, thereby enabling generalization across different properties without requiring retraining for each individual case. Furthermore, the differentiable architecture of our model, combined with its explicit parameter inputs, enables the inverse estimation of physical parameters from observed motion sequences. This capability extends our framework to objects with unknown or unmeasured properties. Experimental results demonstrate state-of-the-art performance in motion reconstruction, robust long-term prediction, geometry generalization, and precise parameters estimation for elastoplastic materials, highlighting its versatility as a unified simulator and inverse analysis tool.
  • Item
    Parallel Constraint Graph Partitioning and Coloring for Realtime Soft-Body Cutting
    (The Eurographics Association, 2025) Yu, Peng; Wang, Ruiqi; Li, Chunlei; Li, Yuxuan; Zhai, Xiao; He, Yuanbo; Wu, Hongyu; Hao, Aimin; Gao, Yang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Real-time simulation of cutting is essential in fields requiring accurate interactions with digital assets, such as virtual manufacturing or surgical training. While Extended Position-Based Dynamics (XPBD) methods are valued for their numerical stability, their reliance on the Gauss-Seidel method leads to two critical limitations when facing high degrees of freedom: the residual stagnation that hinders convergence within limited temporal budget, and a fundamentally sequential nature that limits parallelization, thereby impeding real-time performance. Traditional parallelization approaches often rely on precomputed topological data that becomes outdated during mesh evolution, resulting in suboptimal performance in cutting applications. To address this limitation, this paper introduces a GPU-accelerated algorithm featuring an efficient constraint clustering preprocessing step to accelerate initial solver scheduling, combined with a novel graph coloring technique using GPU-optimized Shortcuts principles for parallel constraint resolution. Experiments show our combination of upfront clustering and dynamic graph re-coloring outperforms existing parallel XPBD implementations, empowering efficient solvers in virtual surgery, product design, and similar scenarios involving continuous geometry updates.
  • Item
    Fast Multi-Body Coupling for Underwater Interactions
    (The Eurographics Association, 2025) Gao, Tianhong; Chen, Xuwen; Li, Xingqiao; Li, Wei; Chen, Baoquan; Pan, Zherong; Wu, Kui; Chu, Mengyu; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Simulating multi-rigid-body interactions in underwater environments is crucial for various downstream applications, such as robotic navigation, manipulation, and locomotion. However, existing approaches either rely on computationally expensive volumetric fluid-rigid simulations or focus solely on single-body dynamics. In this work, we introduce a fast framework for simulating multi-rigid-body coupling in underwater environments by extending the added mass paradigm to capture global interactions in incompressible, irrotational fluids. Our method solves a Boundary Integral Equation (BIE) for the potential flow field, from which we derive the governing equation of motion for multiple underwater rigid bodies using a variational principle. We evaluate our method across a range of underwater tasks, including object gripping and swimming. Compared to state-ofthe- art volumetric fluid solvers, our approach consistently reproduces similar behaviors while achieving up to 13× speedup. The example source code is available at https://github.com/guesss2022/fastMBCUI.
  • Item
    An Adaptive Particle Fission-Fusion Approach for Dual-Particle SPH Fluid
    (The Eurographics Association, 2025) Liu, Shusen; Guo, Yuzhong; Qiao, Ying; He, Xiaowei; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Smoothed Particle Hydrodynamics (SPH) is a classical and popular method for fluid simulation, yet it is inherently susceptible to instabilities under tension or compression, which leads to significant visual artifacts. To overcome the limitation, an adaptive particle fission-fusion approach is proposed within the Dual-particle SPH framework. Specifically, in tension-dominant regions (e.g., fluid splashing), the velocity and pressure calculation points are decoupled to enhance tension stability, while in compression-dominant regions (e.g., fluid interiors), the velocity and pressure points are colocated to preserve compression stability. This adaptive configuration, together with modifications to the Dual-particle projection solver, allows for a unified treatment of fluid behavior across different stress regimes. Additionally, due to the reduced number of virtual particles and an optimized solver initialization, the proposed method achieves significant performance improvements compared to the original Dual-particle SPH method.
  • Item
    Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation
    (The Eurographics Association, 2025) Ren, Kaiwen; Hu, Lei; Zhang, Zhiheng; Ye, Yongjing; Xia, Shihong; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the high semantic level of features extracted from images is inadequate for regressing low-level information, and the extracted features include task-irrelevant information, reducing their compactness and interfering with regression tasks. To address these challenges, we propose TI-Net, a highly versatile visual Network backbone designed to construct a Transformation Isomorphic latent space. Specifically, we employ linear transformations to model geometric transformations in the latent space and ensure that TI-Net aligns them with those in the image space. This ensures that the latent features capture compact, low-level information beneficial for pose estimation tasks. We evaluated TI-Net on the hand pose estimation task to demonstrate the network's superiority. On the DexYCB dataset, TI-Net achieved a 10% improvement in the PA-MPJPE metric compared to specialized state-of-the-art (SOTA) hand pose estimation methods. Our code is available at https://github.com/Mine268/TI-Net.
  • Item
    Skeletal Gesture Recognition Based on Joint Spatio-Temporal and Multi-Modal Learning
    (The Eurographics Association, 2025) Yu, Zhijing; Zhu, Zhongjie; Ge, Di; Tu, Renwei; Bai, Yongqiang; Yang, Yueping; Wang, Yuer; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Hand skeleton-based gesture recognition is a crucial task in human-computer interaction and virtual reality. It aims to achieve precise classification by analyzing the spatio-temporal dynamics of skeleton joints. However, existing methods struggle to effectively model highly entangled spatio-temporal features and fuse heterogeneous Joint, Bone, and Motion (J/B/JM) modalities. These limitations hinder recognition performance. To address these challenges, we propose an Adaptive Spatio-Temporal Network (ASTD-Net) for gesture recognition. Our approach centers on integrated spatio-temporal feature learning and collaborative optimization. First, for spatial feature learning, we design an Adaptive Multi-Subgraph Convolution Module (AMS-GCN) which mitigates spatial coupling interference and enhances structural representation. Subsequently, for temporal feature learning, we introduce a Multi-Scale Dilated Temporal Fusion Module (MD-TFN) that captures multi-granularity temporal patterns, spanning local details to global evolution. This allows for comprehensive modeling of temporal dependencies. Finally, we propose a Self-Supervised Spatio-Temporal Channel Adaptation Module (SSTC-A). Using a temporal discrepancy loss, SSTC-A dynamically optimizes cross-modal dependencies and strengthens alignment between heterogeneous J/B/JM features, enhancing their fusion. On the SHREC'17 and DHG-14/28 datasets, ASTD-Net achieves recognition accuracies of 97.50% and 93.57%, respectively. This performance surpasses current state-of-the-art methods by up to 0.50% and 1.07%. These results verify the effectiveness and superiority of our proposed method.
  • Item
    Global-Local Complementary Representation Network for Vehicle Re-Identification
    (The Eurographics Association, 2025) Deng, Mingchen; Tang, Ziyao; Xiao, Guoqiang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Vehicle Re-Identification (ReID) aims to retrieve images of the same vehicle across multiple non-overlapping cameras. Despite recent advances driven by deep learning, this problem continues to pose challenging due to inter-class similarity and intraclass variation. To address these challenges, we propose a Global-Local Complementary Representation Network (GLCR-Net), which combines global and local features to enhance vehicle ReID accuracy. The global branch employs group convolutions to mitigate overfitting, reduce parameters, and extract comprehensive global features. Meanwhile, the local branch uses a keypoint prediction model to generate keypoint feature maps that are integrated with global features, emphasizing critical regions. Additionally, a Class Activation Mapping (CAM)-based complementary feature learning module is employed to captures features from non-keypoint regions, enriching the feature representation. Experimental results on the VeRi-776 and VehicleID datasets demonstrate that GLCR-Net surpasses state-of-the-art methods in accuracy and generalization. Ablation studies further confirm the effectiveness of group convolutions, keypoint feature integration, and complementary feature learning.
  • Item
    Breaking the Single-Stage Barrier: Synergistic Data-Model Adaptation at Test-Time for Medical Image Segmentation
    (The Eurographics Association, 2025) Zhou, Wenjuan; Chen, Wei; He, Yulin; Wu, Di; Li, Chen; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Domain shift, predominantly caused by variations in medical imaging across different institutions, often leads to a decline in the accuracy of medical image segmentation models. While Test-Time Adaptation (TTA) holds promise to address this issue, existing methods exhibit significant limitations: model adaptation is prone to error accumulation and catastrophic forgetting in continuous domain learning. Meanwhile, data adaptation struggles to achieve deep latent alignment due to the inaccessibility of source domain data. To address these challenges, we propose Synergistic Data-Model Adaptation (SDMA), which innovatively leverages Batch Normalization (BN) layers as a bidirectional bridge to enable a two-stage joint adaptation process. In the data adaptation stage, domain-aware prompts dynamically adjust the BN statistics of incoming test data, achieving low-level distribution alignment in the Fourier space. In the model adaptation stage, we dynamically optimize the BN affine parameters based on strong-weak data augmentation and entropy minimization, enabling adaptation to high-level semantic features. Experiments conducted on five retinal fundus image datasets from various medical institutions demonstrate that our method achieves an average Dice improvement of 1.23% over previous state-of-the-art (SOTA) methods, establishing a new SOTA performance.
  • Item
    Region-Adaptive Low-Light Image Enhancement with Light Effect Suppression and Detail Preservation
    (The Eurographics Association, 2025) Luo, Liheng; Xie, Wantong; Xia, Xiushan; Li, Zerui; Zhao, Yunbo; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Low-light image enhancement seeks to improve the visual quality of images captured under poor illumination, yet existing methods often struggle with unnatural artifacts, overexposure, or detail loss, particularly in challenging real-world scenarios like underground coal mines. We propose a novel unsupervised region-adaptive framework that integrates light effect suppression and detail preservation to address these issues. Leveraging Retinex theory, our approach decomposes images into illumination and reflectance components, employing a region segmentation module to distinguish dark and bright areas for targeted enhancement. A lightweight denoising network mitigates noise, while an adaptive illumination enhancer and light effect suppressor collaboratively optimize illumination to ensure natural appearance and correct visual imbalances. A composite loss function balances brightness enhancement, structural integrity, and artifact suppression across regions. Extensive experiments on the LOL-v2, LSRW and our private datasets demonstrate superior performance. For instance, on our dataset, improvements of 3.26% in BRISQUE, 0.24% in NIQE, and 11.22% in PIQE were achieved compared to state-of-the-art methods, providing visually pleasing results with enhanced brightness, reduced artifacts, and preserved textures, making it well-suited for real-world applications.
  • Item
    Image Reflection Separation via Adaptive Residual Correction and Feature Interaction Enhancement
    (The Eurographics Association, 2025) Ke, Weijian; Mo, Yijun; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Glass reflection superimposes images from both sides of the glass, resulting in severe image quality degradation that significantly impairs the performance of downstream tasks, such as object detection and image understanding. Therefore, it is essential to separate the transmission and reflection layers. However, due to lighting conditions and the material properties of glass, the relationship between the reflected and transmitted components often involves complex linear interactions, which limit the effectiveness of existing methods. Inspired by the observation that transmission components often dominate images with reflection in real-world scenes, we propose an image reflection separation method that integrates adaptive residual correction with feature interaction enhancement. Building upon a linear combination model enhanced with residual correction, we generalize the residual term based on the physical principles of light reflection and transmission. In order to ensure precise spatial alignment between the transparent and real images, We design an image registration mechanism and propose an Adaptive Hybrid Residual Loss, which significantly enhances the model's ability to perceive differences between the transmission and reflection layers, effectively balancing the complexity of linear mixture modeling with the diversity of real-world scenarios. To further highlight the interactive features between reflection and transmission, we incorporate a cross-dimensional attention mechanism into the dual-stream architecture designed for transmission-reflection processing. Extensive experiments and ablation studies show that our method achieves state-of-the-art performance on multiple real-world benchmark datasets, with an average PSNR improvement of 0.66 dB over the current best-performing model.
  • Item
    ER-Diff: A Multi-Scale Exposure Residual-Guided Diffusion Model for Image Exposure Correction
    (The Eurographics Association, 2025) Chen, TianZhen; Liu, Jie; Ru, Yi; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper proposes an Exposure Residual-guided Diffusion Model (ER-Diff) to address the performance limitations of existing image restoration methods in handling non-uniform exposure. Current exposure correction techniques struggle with detail recovery in extreme over/underexposed regions and global exposure balancing. While diffusion models offer powerful generative capabilities for image restoration, effectively leveraging exposure information to guide the denoising process remains underexplored. Additionally, content reconstruction fidelity in severely degraded regions is challenging to ensure. To tackle these issues, ER-Diff explicitly constructs exposure residual features to guide the diffusion process. Specifically, we design a multi-scale exposure residual guidance module that first computes the residual between the input image and an ideally exposed reference, then transforms it into hierarchical feature representations via a multi-scale extraction network, and finally integrates these features progressively into the denoising process. This design enhances feature representation in locally distorted exposure areas while maintaining global exposure consistency. By decoupling content reconstruction and exposure correction, our method achieves more natural exposure adjustment with better detail preservation while ensuring content authenticity. Extensive experiments demonstrate that ER-Diff outperforms state-of-the-art exposure correction methods in both quantitative and qualitative evaluations, particularly in complex lighting conditions, effectively balancing detail retention and exposure correction.
  • Item
    Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
    (The Eurographics Association, 2025) Fujiwara, Haruo; Mukuta, Yusuke; Harada, Tatsuya; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Recent advances in text-driven 3D scene editing and stylization, which leverage the powerful capabilities of 2D generative models, have demonstrated promising outcomes. However, challenges remain in ensuring high-quality stylization and view consistency simultaneously. Moreover, applying style consistently to different regions or objects in the scene with semantic correspondence is a challenging task. To address these limitations, we introduce techniques that enhance the quality of 3D stylization while maintaining view consistency and providing optional region-controlled style transfer. Our method achieves stylization by re-training an initial 3D representation using stylized multi-view 2D images of the source views. Therefore, ensuring both style consistency and view consistency of stylized multi-view images is crucial. We achieve this by extending the style-aligned depth-conditioned view generation framework, replacing the fully shared attention mechanism with a single reference-based attention-sharing mechanism, which effectively aligns style across different viewpoints. Additionally, inspired by recent 3D inpainting methods, we utilize a grid of multiple depth maps as a single-image reference to further strengthen view consistency among stylized images. Finally, we propose Multi-Region Importance-Weighted Sliced Wasserstein Distance Loss, allowing styles to be applied to distinct image regions using segmentation masks from off-the-shelf models. We demonstrate that this optional feature enhances the faithfulness of style transfer and enables the mixing of different styles across distinct regions of the scene. Experimental evaluations, both qualitative and quantitative, demonstrate that our pipeline effectively improves the results of text-driven 3D stylization.
  • Item
    Latent Interpretation for Diffusion Autoencoders via Integrated Semantic Reconstruction
    (The Eurographics Association, 2025) Ju, Yixuan; Tan, Xuan; Zhu, Zhenyang; Li, Jiyi; Mao, Xiaoyang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Latent interpretation enables controllable image editing by discovering semantic components in the latent space of generative models. While prior works have primarily focused on GANs, their limited inversion capabilities and generation quality hinder their applicability in diverse editing tasks. In this paper, we propose a new framework for latent interpretation on pretrained diffusion autoencoders, combining the editing flexibility of latent-based methods with the generation quality of diffusion models. Our key insight is to perform semantic guidance directly in the latent space, thereby avoiding costly pixel-space feedback and enabling end-to-end training. To this end, we introduce a bidirectional editing strategy and an integrated lightweight semantic autoencoder to effectively constrain semantic directions. Our method enables fine-grained and disentangled manipulation across various image editing tasks, including facial attributes, face pose, and style transfer. Extensive experiments demonstrate state-of-the-art performance in both visual quality and editing disentanglement, compared to widely-used GAN-based and diffusion-based baselines. To the best of our knowledge, this work represents a novel step toward identify explicit semantic directions in the latent space of diffusion models, complementing the research on latent interpretation beyond GANs toward more flexible and precise image editing. Our code available at https://github.com/Xenithon/LIDA.
  • Item
    PF-UCDR: A Local-Aware RGB-Phase Fusion Network with Adaptive Prompts for Universal Cross-Domain Retrieval
    (The Eurographics Association, 2025) Wu, Yiqi; Hu, Ronglei; Wu, Huachao; He, Fazhi; Zhang, Dejun; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Universal Cross-Domain Retrieval (UCDR) aims to match semantically related images across domains and categories not seen during training. While vision-language pre-trained models offer strong global alignment, we are inspired by the observation that local structures, such as shapes, contours, and textures, often remain stable across domains, and thus propose to model them explicitly at the patch level. We present PF-UCDR, a framework built upon frozen vision-language backbones that performs patch-wise fusion of RGB and phase representations. Central to our design is a Fusing Vision Encoder, which applies masked cross-attention to spatially aligned RGB and phase patches, enabling fine-grained integration of complementary appearance and structural cues. Additionally, we incorporate adaptive visual prompts that condition image encoding based on domain and class context. Local and global fusion modules aggregate these enriched features, and a two-stage training strategy progressively optimizes alignment and retrieval objectives. Experiments on standard UCDR benchmarks demonstrate that PF-UCDR significantly outperforms existing methods, validating the effectiveness of structure-aware local fusion grounded in multimodal pretraining. Our code is publicly available at https://github.com/djzgroup/PF-UCDR.
  • Item
    KIN-FDNet:Dual-Branch KAN-INN Decomposition Network for Multi-Modality Image Fusion
    (The Eurographics Association, 2025) Dong, Aimei; Meng, Hao; Chen, Zhen; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Multi-modality image fusion (MMIF) aims to integrate information from different source images to preserve the complementary information of each modality, such as feature highlights and texture details. However, current fusion methods fail to effectively address the inter-modality interference and feature redundancy issues. To address this issue, we propose an end-to-end dualbranch KAN-INN decomposition network (KIN-FDNet) with an effective feature decoupling mechanism for separating shared and specific features. It first employs a gated attention-based Transformer module for cross-modal shallow feature extraction. Then, we embed KAN into the Transformer architecture to extract low-frequency global features and solve the problem of low parameter efficiency in multi-branch models. Meanwhile, an invertible neural network (INN) processes high-frequency local information to preserve fine-grained modality-specific details. In addition, we design a dual-frequency cross-fusion module to promote information interaction between low and high frequencies to obtain high-quality fused images. Extensive experiments on visible infrared (VIF) and medical image fusion (MIF) tasks demonstrate the superior performance and generalization ability of our KIN-FDNet framework.
  • Item
    Neural Shadow Art
    (The Eurographics Association, 2025) Wang, Caoliwen; Deng, Bailin; Zhang, Juyong; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Shadow art is a captivating form of sculptural expression where the projection of a sculpture in a specific direction reveals a desired shape with high precision. In this work, we introduce Neural Shadow Art, which leverages implicit occupancy function representation to significantly expand the possibilities of shadow art. This representation enables the design of high-quality, 3D-printable geometric models with arbitrary topologies at any resolution, surpassing previous voxel- and mesh-based methods. Our method provides a more flexible framework, enabling projections to match input binary images under various light directions and screen orientations, without requiring light sources to be perpendicular to the screens. Furthermore, we allow rigid transformations of the projected geometries relative to the input binary images and simultaneously optimize light directions and screen orientations to ensure that the projections closely resemble the target images, especially when dealing with inputs of complex topologies. In addition, our model promotes surface smoothness and reduces material usage. This is particularly advantageous for efficient industrial production and enhanced artistic effect by generating compelling shadow art that avoids trivial, intersecting cylindrical structures. In summary, we propose a more flexible representation for shadow art, significantly improving projection accuracy while simultaneously meeting industrial requirements and delivering awe-inspiring artistic effects.
  • Item
    Reducing Visible Staircasing Artifacts Through Printing Orientation Using a Perception-Driven Metric
    (The Eurographics Association, 2025) Yurtsever, Mehmet Ata; Didyk, Piotr; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    3D printing is widely used for prototyping and fabricating custom designs. Due to the discretization introduced during printing, the quality of the fabricated surfaces often suffers from so-called staircasing artifacts. While all 3D printers produce these artifacts, their severity depends on the printing resolution. Thus, these artifacts are particularly pronounced in low- to medium-cost printers, which are commonly used by home users, hobbyists, and enthusiasts of 3D printing. Changing the printing orientation allows for reducing the artifacts, enabling more accurate surface reproduction. While several previous works exploited this idea, they formulated the problem based on the geometrical accuracy of surface reproduction. This paper takes a different approach that focuses on the perception of the surface appearance. Our work is motivated by the fact that the visual severity of the artifacts depends on the characteristics of the patterns that the staircasing produces. These are also influenced by the viewing conditions, i.e., lighting and viewing orientations. Consequently, we develop in this paper a perception-inspired technique for quantifying the visibility of staircasing artifacts that takes the above factors into consideration. It is grounded in the human contrast sensitivity function, which models the ability of the human visual system to detect spatial patterns. Using the method, we propose an optimization procedure for finding the printing orientation for 3D models, which minimizes the visibility of staircasing artifacts. We evaluate our method against geometric approaches across a range of 3D models and viewing conditions. Our user study confirms the effectiveness of our approach in reducing the visual impact of staircasing artifacts.
  • Item
    GaussianMatch: Adaptive Learning Continuous Surfaces for Light Field Depth Estimation
    (The Eurographics Association, 2025) Sun, Zexin; Chen, Rongshan; Wang, Yu; Cui, Zhenglong; Yang, Da; Li, Siyang; Huang, Xuefei; Sheng, Hao; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Light field (LF) depth estimation plays a vital role in computational imaging by reconstructing 3D structures from multiple viewpoints. However, images are merely discrete expressions of scenes due to the resolution constraints of cameras, leading to depth discontinuities and outliers-particularly in textureless or occluded regions, degrading reconstruction coherence. To address the challenges mentioned above, we propose GaussianMatch, a probabilistic depth estimation framework that models per-pixel depth as a learnable Gaussian distribution in continuous space. This scheme effectively alleviates the discretization problem of LF images by adaptively reconstructing continuous surfaces, while enabling uncertainty-aware optimization.Furthermore, the framework naturally fuses information among adjacent pixels and adapts each Gaussian's variance according to scene complexity, achieving robustness in both texture-rich and ambiguous regions. We further design GaussianNet, which regresses per-pixel Gaussian parameters and generates the final depth map via Gaussian accumulation. Extensive experiments on multiple LF benchmarks demonstrate that GaussianNet achieves state-of-the-art accuracy, with significant improvements in handling depth discontinuities and occlusions.
  • Item
    CGS: Continual Gaussian Splatting for Evolving 3D Scene Reconstruction
    (The Eurographics Association, 2025) Yang, Shuojin; Chen, Haoxiang; Mu, Taijiang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    3D Gaussian Splatting (3DGS) has gained significant attention for its fast optimization and high-quality rendering capabilities. However, in the context of continual scene reconstruction, optimizing newly observed regions often leads to degradation in previously reconstructed areas due to changes in camera viewpoints. To address this issue, we propose Continual Gaussian Splatting (CGS)-an efficient incremental reconstruction method that updates dynamic scenes using only a limited amount of new data while minimizing computational overhead. CGS is composed of three core components. First, we introduce a similarity-based registration algorithm that leverages the strong semantic understanding and translation invariance of pretrained Transformers to identify and align similar regions between new and existing scenes. These regions are then modeled as Gaussian Mixture Models (GMMs) to handle sparsity and outliers in point clouds, ensuring geometric consistency across scenes. Second, we propose Continual Gaussian Optimization (CGO), an importance-aware optimization strategy. By computing the Fisher Information Matrix, we evaluate the significance of each Gaussian point in the old scene and automatically restrict updates to those deemed critical, allowing only non-sensitive components to be adjusted. This ensures the preservation of the original scene while efficiently integrating new content. Finally, to address remaining issues such as geometric inconsistencies, blurring, and ghosting artifacts during optimization, we introduce a series of geometric regularization techniques. These terms guide the optimization toward geometrically coherent 3D structures, ultimately enhancing rendering quality. Extensive experiments demonstrate that CGS effectively mitigates forgetting and significantly improves overall reconstruction fidelity.
  • Item
    Distance-Aware Tri-Perspective View for Efficient 3D Perception in Autonomous Driving
    (The Eurographics Association, 2025) Tang, Yutao; Zhao, Jigang; Qin, Zhengrui; Qiu, Rui; Zhao, Lingying; Ren, Jie; Chen, Guangxi; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Three-dimensional environmental perception remains a critical bottleneck in autonomous driving, where existing vision-based dense representations face an intractable trade-off between spatial resolution and computational complexity. Current methods, including Bird's Eye View (BEV) and Tri-Perspective View (TPV), apply uniform perception precision across all spatial regions, disregarding the fundamental safety principle that near-field objects demand high-precision detection for collision avoidance while distant objects permit lower initial accuracy. This uniform treatment squanders computational resources and constrains real-time deployment. We introduce Distance-Aware Tri-Perspective View (DA-TPV), a novel framework that allocates computational resources proportional to operational risk. DA-TPV employs a hierarchical dual-plane architecture for each viewing direction: low-resolution planes capture global scene context while high-resolution planes deliver fine-grained perception within safety-critical reaction zones. Through distance-adaptive feature fusion, our method dynamically concentrates processing power where it most directly impacts vehicle safety. Extensive experiments on nuScenes demonstrate that DA-TPV matches or exceeds single high-resolution TPV performance while reducing memory consumption by 26.3% and achieving real-time inference. This work establishes distance-aware perception as a practical paradigm for deploying sophisticated three-dimensional understanding within automotive computational constraints. Code is available at https://github.com/yytang2012/DA-TPVFormer.
  • Item
    GaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splatting
    (The Eurographics Association, 2025) Du, Feilong; Zhang, Yalan; Ji, Yihang; Wang, Xiaokun; Yao, Chao; Kosinka, Jiri; Frey, Steffen; Telea, Alexandru; Ban, Xiaojuan; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Fluid simulation typically depends on manual modeling and visual assessment to achieve desired outcomes, which lacks objectivity and efficiency. To address this limitation, we propose GaussFluids, a novel approach for directly reconstructing temporally and spatially continuous Lagrangian fluid particles from videos. We employ a Lagrangian particle-based method instead of an Eulerian grid as it provides a direct spatial mass representation and is more suitable for capturing fine fluid details. First, to make discrete fluid particles differentiable over time and space, we extend Lagrangian particles with Gaussian probability densities, termed Gaussian Particles, constructing a differentiable fluid particle renderer that enables direct optimization of particle positions from visual data. Second, we introduce a fixed-length transform feature for each Gaussian Particle to encode pose changes over continuous time. Next, to preserve fundamental fluid physics-particularly incompressibility-we incorporate a density-based soft constraint to guide particle distribution within the fluid. Furthermore, we propose a hybrid loss function that focuses on maintaining visual, physical, and geometric consistency, along with an improved density optimization module to efficiently reconstruct spatiotemporally continuous fluids. We demonstrate the effectiveness of GaussFluids on multiple synthetic and real-world datasets, showing its capability to accurately reconstruct temporally and spatially continuous, physically plausible Lagrangian fluid particles from videos. Additionally, we introduce several downstream tasks, including novel view synthesis, style transfer, frame interpolation, fluid prediction, and fluid editing, which illustrate the practical value of GaussFluids.
  • Item
    Unsupervised 3D Shape Parsing with Primitive Correspondence
    (The Eurographics Association, 2025) Zhao, Tianshu; Guan, Yanran; Kaick, Oliver van; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    3D shape parsing, the process of analyzing and breaking down a 3D shape into components or parts, has become an important task in computer graphics and vision. Approaches for shape parsing include segmentation and approximation methods. Approximation methods often represent shapes with a set of primitives fit to the shapes, such as cuboids, cylinders, or superquadrics. However, existing approximation methods typically rely on a large number of initial primitives and aim to maximize their coverage of the target shape, without accounting for correspondences among the primitives. In this paper, we introduce a novel 3D shape approximation method that integrates reconstruction and correspondence into a single objective, providing approximations that are consistent across the input set of shapes. Our method is unsupervised but also supports supervised learning. Experimental results demonstrate that integrating correspondences into the fitting process not only provides consistent correspondences across a set of input shapes, but also improves approximation quality when using a small number of primitives. Moreover, although correspondences are estimated in an unsupervised manner, our method effectively leverages this knowledge, leading to improved approximations.
  • Item
    SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing
    (The Eurographics Association, 2025) Zhou, Jin; Yang, Hongliang; Xu, Pengfei; Huang, Hui; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Neural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model highlevel semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.
  • Item
    VF-Plan: Bridging the Art Gallery Problem and Static LiDAR Scanning with Visibility Field Optimization
    (The Eurographics Association, 2025) Xiong, Biao; Zhang, LongJun; Huang, Ruiqi; Zhou, Junwei; Jafri, Syed Riaz un Nabi; Wu, Bojian; Li, Fashuai; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Viewpoint planning is critical for efficient 3D data acquisition in applications such as 3D reconstruction, building life-cycle management, navigation, and interior decoration. However, existing methods often neglect key optimization objectives specific to static LiDAR systems, resulting in redundant or disconnected viewpoint networks. The viewpoint planning problem (VPP) extends the classical Art Gallery Problem (AGP) by requiring full coverage, strong registrability, and coherent network connectivity under constrained sensor capabilities. To address these challenges, we introduce a novel Visibility Field (VF) that accurately captures the directional and range-dependent visibility properties of static LiDAR scanners. We further observe that visibility information naturally converges onto a 1D skeleton embedded in the 2D space, enabling significant searching space reduction. Leveraging these insights, we develop a greedy optimization algorithm tailored to the VPP, which constructs a minimal yet fully connected Viewpoint Network (VPN) with low redundancy. Experimental evaluations across diverse indoor and outdoor scenarios confirm the scalability and robustness of our method. Compared to expert-designed VPNs and existing state-of-the-art approaches, our algorithm achieves comparable or fewer viewpoints while significantly enhancing connectivity. In particular, it reduces the weighted average path length by approximately 95%, demonstrating substantial improvements in compactness and structural efficiency. Code is available at https://github.com/xiongbiaostar/VFPlan.
  • Item
    Generating 3D Hair Strips from Partial Strands using Diffusion Model
    (The Eurographics Association, 2025) Lee, Gyeongmin; Jang, Wonjong; Lee, Seungyong; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Animation-friendly hair representation is essential for real-time applications such as interactive character systems. While lightweight strip-based models are increasingly adopted as alternatives to strand-based hair for computational efficiency, creating such hair strips based on the hairstyle shown in a single image remains laborious. In this paper, we present a diffusion model-based framework for 3D hair strip generation using sparse strands extracted from a single portrait image. Our key idea is to formulate this task as an inpainting problem solved through a diffusion model operating in the UV parameter space of the head scalp. We parameterize both strands and strips on a shared UV scalp map, enabling the diffusion model to learn their correlations. We then perform spatial and channel-wise inpainting to reconstruct complete strip representations from partially observed strand maps. To train our diffusion model, we address the data scarcity problem of 3D hair strip models by constructing a large-scale strand-strip paired dataset through our adaptive clustering algorithm that converts groups of hair strands into strip models. Comprehensive qualitative and quantitative evaluations demonstrate that our framework effectively reconstructs high-quality hair strip models from an input image while preserving characteristic styles of strips. Furthermore, we show that the generated strips can be directly integrated into rigging-based animation workflows for real-time platforms such as games.
  • Item
    Attention-Guided Multi-scale Neural Dual Contouring
    (The Eurographics Association, 2025) Wu, Fuli; Hu, Chaoran; Li, Wenxuan; Hao, Pengyi; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Reconstructing high-quality meshes from binary voxel data is a fundamental task in computer graphics. However, existing methods struggle with low information density and strong discreteness, making it difficult to capture complex geometry and long-range boundary features, often leading to jagged surfaces and loss of sharp details.We propose an Attention-Guided Multiscale Neural Dual Contouring (AGNDC) method to address this challenge. AGNDC refines surface reconstruction through a multi-scale framework, using a hybrid feature extractor that combines global attention and dynamic snake convolution to enhance perception of long-range and high-curvature features. A dynamic feature fusion module aligns multi-scale predictions to improve local detail continuity, while a geometric postprocessing module further refines mesh boundaries and suppresses artifacts. Experiments on the ABC dataset demonstrate the superior performance of AGNDC in both visual and quantitative metrics. It achieves a Chamfer Distance (CD×105) of 9.013 and an F-score of 0.440, significantly reducing jaggedness and improving surface smoothness.
  • Item
    World-Space Direct and Indirect Lighting Sample Reuse with Persistent Reservoirs
    (The Eurographics Association, 2025) Yuan, JunPing; Wang, Chen; Sun, Qi; Guo, Jie; Bei, Jia; Zhang, Yan; Guo, Yanwen; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    In the context of hardware-accelerated real-time ray tracing, existing spatiotemporal resampling techniques are still constrained by screen-space dependencies, which may lead to reuse failures. To address this issue, we propose a world-space resampling method based on a hybrid spatial structure that combines uniform grids and octrees. This persistent structure, which remains unchanged with respect to camera motion, can efficiently partition scenes while preserving geometric details. Our method begins with generating initial light samples, then remaps these samples to the spatial structure. Spatial reuse occurs entirely within individual spatial nodes. For direct illumination, we determine the spatial node of each shading point and select the world-space reservoir from that node to obtain a light sample. For indirect illumination, we trace a BRDF ray and use the world-space reservoir within the spatial node at the hit point to improve the NEE. This unified approach enables joint sample reuse for both direct and indirect illumination. Our experiments show that the proposed method achieves 20-70% reduction in RelMSE compared to screen-space ReSTIR and previous world-space methods under equal-time comparison, with 2× faster convergence rates and superior temporal stability under rapid camera motion.
  • Item
    Iterative Lightmap Updates for Scene Editing
    (The Eurographics Association, 2025) Lu, Guowei; Peters, Christoph; Kellnhofer, Petr; Eisemann, Elmar; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Lightmaps are popular for precomputed global illumination, but require costly recomputation when the scene changes. We present the theory and an iterative algorithm to update lightmaps efficiently, when objects are inserted or removed. Our method is based on path tracing, but focuses on updates to those paths that are affected by the scene change. Using an importance sampling scheme, our solution substantially accelerates convergence. Our GPU implementation is well-suited for interactive scene editing scenarios.
  • Item
    Stable Sample Caching for Interactive Stereoscopic Ray Tracing
    (The Eurographics Association, 2025) Philippi, Henrik; Jensen, Henrik Wann; Frisvad, Jeppe Revall; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We present an algorithm for interactive stereoscopic ray tracing that decouples visibility from shading and enables caching of radiance results for temporally stable and stereoscopically consistent rendering. With an outset in interactive stable ray tracing, we build a screen space cache that carries surface samples from frame to frame via forward reprojection. Using a visibility heuristic, we adaptively trace the samples and achieve high performance with little temporal artefacts. Our method also serves as a shading cache, which enables temporal reuse and filtering of shading results in virtual reality (VR). We demonstrate good antialiasing and temporal coherence when filtering geometric edges. We compare our sample-based radiance caching that operates in screen space with temporal antialiasing (TAA) and a hash-based shading cache that operates in a voxel representation of world space. In addition, we show how to extend the shading cache into a radiance cache. Finally, we use the per-sample radiance values to improve stereo vision by employing stereo blending with improved estimates of the blending parameter between the two views.
  • Item
    Uni-IR: One Stage is Enough for Ambiguity-Reduced Inverse Rendering
    (The Eurographics Association, 2025) Ge, Wenhang; Feng, Jiawei; Shen, Guibao; Chen, Ying-Cong; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Inverse rendering aims to decompose an image into geometry, materials, and lighting. Recently, Neural Radiance Fields (NeRF) based inverse rendering has significantly advanced, bridging the gap between NeRF-based models and conventional rendering engines. Existing methods typically adopt a two-stage optimization approach, beginning with volume rendering for geometry reconstruction, followed by physically based rendering (PBR) for materials and lighting estimation. However, the inherent ambiguity between materials and lighting during PBR, along with the suboptimal nature of geometry reconstruction by volume rendering, compromises the outcomes. To address these challenges, we introduce Uni-IR, a unified framework that imposes mutual constraints to alleviate ambiguity by integrating volume rendering and physically based rendering. Specifically, we employ a physically-based volume rendering (PBVR) approach that incorporates PBR concepts into volume rendering, directly facilitating connections with materials and lighting, in addition to geometry. Both rendering methods are utilized simultaneously during optimization, imposing mutual constraints and optimizing geometry, materials, and lighting synergistically. By employing a carefully designed unified representation for both lighting and materials, Uni-IR achieves high-quality geometry reconstruction, materials, and lighting estimation across various object types.
  • Item
    By-Example Synthesis of Vector Textures
    (The Eurographics Association, 2025) Palazzolo, Christopher; Kaick, Oliver van; Mould, David; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We propose a new method for synthesizing an arbitrarily sized novel vector texture given a single raster exemplar. In an analysis phase, our method first segments the exemplar to extract primary textons, secondary textons, and a palette of background colors. Then, it clusters the primary textons into categories based on visual similarity, and computes a descriptor to capture each texton's neighborhood and inter-category relationships. In the synthesis phase, our method first constructs a gradient field with a set of control points containing colors from the background palette. Next, it places primary textons based on the descriptors, in order to replicate a similar texton context as in the exemplar. The method also places secondary textons to complement the background detail. We compare our method to previous work with a wide range of perceptual-based metrics, and show that we are able to synthesize textures directly in vector format with quality similar to methods based on raster image synthesis.
  • Item
    Motion Vector-Based Frame Generation for Real-Time Rendering
    (The Eurographics Association, 2025) Ha, Inwoo; Ahn, Young Chun; Yoon, Sung-eui; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    The demand for high frame rate rendering is rapidly increasing, especially in the graphics and gaming industries. Although recent learning-based frame interpolation methods have demonstrated promising results, they have not yet achieved the quality required for real-time gaming. High-quality frame interpolation is critical for rendering faster, dynamic motion during gameplay. In graphics, motion vectors are typically favored over optical flow due to their accuracy and efficiency in game engines. However, motion vectors alone are insufficient for frame interpolation, as they lack bilateral motions for the target frame to interpolate and struggle with capturing non-geometric movements. To address this, we propose a novel method that leverages fast, low-cost motion vectors as guiding flows, integrating them into a task-specific intermediate flow estimation process. Our approach employs a combined motion and image context encoder-decoder to produce more accurate intermediate bilateral flows. As a result, our method significantly improves interpolation quality and achieves state-of-the-art performance in rendered content.
  • Item
    CoSketcher: Collaborative and Iterative Sketch Generation with LLMs under Linguistic and Spatial Control
    (The Eurographics Association, 2025) Mei, Liwen; Guan, Manhao; Zheng, Yifan; Zhang, Dongliang; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Sketching serves as both a medium for visualizing ideas and a process for creative iteration. While early neural sketch generation methods rely on category-specific data and lack generalization and iteration capability, recent advances in Large Language Models (LLMs) have opened new possibilities for more flexible and semantically guided sketching. In this work, we present CoSketcher, a controllable and iterative sketch generation system that leverages the prior knowledge and textual reasoning abilities of LLMs to align with the creative iteration process of human sketching. CoSketcher introduces a novel XML-style sketch language that represents stroke-level information in structured format, enabling the LLM to plan and generate complex sketches under both linguistic and spatial control. The system supports visual appealing sketch construction, including skeleton-contour decomposition for volumetric shapes and layout-aware reasoning for object relationships. Through extensive evaluation, we demonstrate that our method generates expressive sketches across both in-distribution and out-of-distribution categories, while also supporting scene-level composition and controllable iteration. Our method establishes a new paradigm for controllable sketch generation using off-the-shelf LLMs, with broad implications for creative human-AI collaboration.
  • Item
    Easy Modeling of Man-Made Shapes in Virtual Reality
    (The Eurographics Association, 2025) Tang, Haoyu; Gao, Fancheng; Choo, Kenny Tsu Wei; Bickel, Bernd; Song, Peng; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Virtual Reality (VR) offers a promising platform for modeling man-made shapes by enabling immersive, hands-on interaction with these 3D shapes. Existing VR tools require either a complex user interface or a post-processing to model fabricable man-made shapes. In this paper, we present a VR tool that enables general users to interactively model man-made shapes for personalized fabrication, simply by using four common hand gestures as the interaction input. This is achieved by proposing an approach that models complex man-made shapes using a small set of geometric operations, and then designing a user interface that intuitively maps four common hand gestures to these operations. In our shape modeling approach, each shape part is modeled as a generalized cylinder with a specific shape type and iteratively assembled in a structure-aware manner to form a fabricable and usable man-made shape. In our user interface, each hand gesture is associated with a specific kind of interaction tasks and is intelligently utilized for performing the small set of operations to create, edit, and assemble generalized cylinders. A user study was conducted to demonstrate that our VR tool allows general users to effectively and creatively model a variety of man-made shapes, some of which have been 3D printed to validate their fabricability and usability.
  • Item
    ChromBrain Wall: A Virtual Reality Game Featuring Customized Full-Body Movement for Long-Term Physical and Cognitive Training in Older Adults
    (The Eurographics Association, 2025) Wu, Hao; Zhao, Juanjuan; Li, Aoyu; Qiang, Yan; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Aging brings challenges to the daily lives of older adults due to the decline in physical and cognitive functions. Although virtual reality (VR) exercise games can promote the physical and cognitive health of older adults, existing games are not suitable for personalized continuous training for the elderly due to unreasonable cognitive activation patterns, exercise task designs, and difficulty settings. To address this, we developed ChromaBrain Wall, a VR cognitive training exercise game with customized full-body movements, for the long-term exercise and cognitive inhibition training of healthy older adults. We then conducted an 8-month longitudinal user study on 40 older adults aged 65 and above, and the results showed that after the training, the older adults' exercise performance and cognitive inhibition abilities were significantly enhanced, and these benefits lasted for 6 months. Moreover, qualitative feedback indicated that the older adults had a positive attitude towards long-term use of ChromaBrain Wall, which increased their training motivation and compliance. This shows that ChromaBrain Wall has both short-term and long-term effects in enhancing the exercise performance and cognitive inhibition of older adults, providing a new approach for the health intervention of the elderly.
  • Item
    C2Views: Knowledge-based Colormap Design for Multiple-View Consistency
    (The Eurographics Association, 2025) Hou, Yihan; Ye, Yilin; Wang, Liangwei; Qu, Huamin; Zeng, Wei; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Multiple-view (MV) visualization provides a comprehensive and integrated perspective on complex data, establishing itself as an effective method for visual communication and exploratory data analysis. While existing studies have predominantly focused on designing explicit visual linkages and coordinated interactions to facilitate the exploration of MV visualizations, these approaches often demand extra graphical and interactive effort, overlooking the potential of color as an effective channel for encoding data and relationships. Addressing this oversight, we introduce C2Views, a new framework for colormap design that implicitly shows the relation across views. We begin by structuring the components and their relationships within MVs into a knowledge-based graph specification, wherein colormaps, data, and views are denoted as entities, and the interactions among them are illustrated as relations. Building on this representation, we formulate the design criteria as an optimization problem and employ a genetic algorithm enhanced by Pareto optimality, generating colormaps that balance single-view effectiveness and multiple-view consistency. Our approach is further complemented with an interactive interface for user-intended refinement. We demonstrate the feasibility of C2Views through various colormap design examples for MVs, underscoring its adaptability to diverse data relationships and view layouts. Comparative user studies indicate that our method outperforms the existing approach in facilitating color distinction and enhancing multiple-view consistency, thereby simplifying data exploration processes.
  • Item
    Structural Entropy Based Visualization of Social Networks
    (The Eurographics Association, 2025) Xue, Mingliang; Chen, Lu; Wei, Chunyu; Hou, Shuowei; Cui, Lizhen; Deussen, Oliver; Wang, Yunhai; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Social networks exhibit the small-world phenomenon, characterized by highly interconnected nodes (clusters) with short average path distances. While force-directed layouts are widely employed to visualize such networks, they often result in visual clutter, obscuring community structures due to high node connectivity. In this paper, we present a novel approach that leverages structural entropy and coding trees to enhance community visualization in social networks. Our method computes the structural entropy of graph partitions to construct coding trees that guide hierarchical partitioning with O(E) time complexity. These partitions are then used to assign edge weights that influence attractive forces in the layout, promoting clearer community separation while preserving local cohesion. We evaluate our approach through both quantitative and qualitative comparisons with state-of-the-art community-aware layout algorithms and present two case studies that highlight its practical utility in the analysis of real-world social networks. The results demonstrate that our method enhances community visibility without compromising layout performance. Code and demonstrations are available at https://github.com/IDEAS-Laboratory/SEL.
  • Item
    CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering
    (The Eurographics Association, 2025) Jin, Qiangguo; Zheng, Xianyao; Cui, Hui; Sun, Changming; Fang, Yuqi; Cong, Cong; Su, Ran; Wei, Leyi; Xuan, Ping; Wang, Junbo; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments between vision and language. Moreover, classification-based methods rely on predefined answer sets. Treating this task as a simple classification problem may make it unable to adapt to the diversity of free-form answers and overlook the detailed semantic information of free-form answers. In order to tackle these challenges, we introduce a Cross-Mamba Interaction based Multi-Task Learning (CMI-MTL) framework that learns cross-modal feature representations from images and texts. CMI-MTL comprises three key modules: fine-grained visual-text feature alignment (FVTA), cross-modal interleaved feature representation (CIFR), and free-form answer-enhanced multi-task learning (FFAE). FVTA extracts the most relevant regions in image-text pairs through fine-grained visual-text feature alignment. CIFR captures cross-modal sequential interactions via cross-modal interleaved feature representation. FFAE leverages auxiliary knowledge from open-ended questions through free-form answerenhanced multi-task learning, improving the model's capability for open-ended Med-VQA. Experimental results show that CMI-MTL outperforms the existing state-of-the-art methods on three Med-VQA datasets: VQA-RAD, SLAKE, and OVQA. Furthermore, we conduct more interpretability experiments to prove the effectiveness. The code is publicly available at https://github.com/BioMedIA-repo/CMI-MTL.
  • Item
    Semi-supervised Dual-teacher Comparative Learning with Bidirectional Bisect Copy-paste for Medical Image Segmentation
    (The Eurographics Association, 2025) Fang, Jiangxiong; Qi, Shikuan; Liu, Huaxiang; Fu, Youyao; Zhang, Shiqing; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Semi-supervised learning leverages limited pixel-level annotated data and abundant unlabeled data to achieve effective semantic image segmentation. To address this, we propose a semi-supervised learning framework, integrated with a bidirectional bisect copy-paste (B2P) mechanism. We introduce a B2CP strategy applied to labeled and unlabeled data in the second teacher network, preserving both data types to enhance training diversity. This mechanism, coupled with copy-paste-based supervision for the student network, effectively mitigates interference from uncontrollable regions. Extensive experiments on the ACDC public datasets demonstrate the efficiency of the proposed model. It surpasses the fully supervised U-Net at a 5% labeled data and 20% labeled data.
  • Item
    Self-Supervised Neural Global Illumination for Stereo-Rendering
    (The Eurographics Association, 2025) Zhang, Ziyang; Simo-Serra, Edgar; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    We propose a novel neural global illumination baking method for real-time stereoscopic rendering, with applications to virtual reality. Naively, applying neural global illumination to stereoscopic rendering requires running the model per eye, which doubles the computational cost making it infeasible for real-time virtual reality applications. Training a stereoscopic model from scratch is also impractical, as it will require additional path tracing ground truth for both eyes. We overcome these limitations by first training a common neural global illumination baking model using a single eye dataset. We then use self-supervised learning to train a second stereoscopic model using the first model as a teacher model, where we also transfer the weights of the first model to the second model to accelerate the training process. Furthermore, our spatial coherence loss encourages consistency between the rendering for two eyes. Experiments show our method achieves the same quality as the original single-eye model with minimal overhead, enabling real-time performance in virtual reality.
  • Item
    3D Curve Development with Crossing and Twisting from 2D Drawings
    (The Eurographics Association, 2025) Setiadi, Aurick Daniel Franciskus; Lean, Jeng Wen Joshua; Kao, Hao-Che; Hung, Shih-Hsuan; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Designing 3D curves with specified crossings and twistings often requires tedious view adjustments. We present a 3D curve development from 2D drawing with controlled crossings and twistings. We introduce a two-strand 2D diagram that lets users sketch with explicit crossing and twisting assignments. The system extracts feature points from the 2D diagram and uses them as 3D control points. It assigns the heights and over/under relationships of the control points via an optimization and then generates twisted 3D curves using B-splines. An interactive interface links the 2D diagram to the evolving 3D curves, enabling real-time iteration. We validate our method on diverse sketches, compare it with traditional 3D curve construction, and demonstrate its utility for elastic wire art via physics-based animation.
  • Item
    SampleMono: Multi-Frame Spatiotemporal Extrapolation of 1-spp Path-Traced Sequences via Transfer Learning
    (The Eurographics Association, 2025) Derin, Mehmet Oguz; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Path-traced sequences at one sample per pixel (1-spp) are attractive for interactive previews but remain severely noisy, particularly under caustics, indirect lighting, and volumetric media. We present SampleMono, a novel approach that performs multi-frame spatiotemporal extrapolation of low-resolution and low-sample Monte Carlo sequences without requiring auxiliary buffers or scene-specific information. We transfer and prune a pre-trained video generation backbone and fine-tune it on SampleMono GYM, a synthetic Monte Carlo dataset, to generate four clean high-resolution frames from a longer window of noisy inputs, thereby decoupling render and presentation timelines. Our experiments demonstrate that by combining a frozen VAE encoder-decoder and training of a video generation model pruned to two transformer layers, our pipeline can both provide spatial upsampling and temporal extrapolation to a long sequence of 16 RGB frames of 50 milliseconds time delta between frames at 256×144 resolution with severe Monte Carlo noise, generating subsequent four RGB frames of 12.5 milliseconds time delta between frames at 1280×720 resolution with substantially reduced noise at varying quality while fitting VRAM budget of 5GB. We plan to publish the code for data GYM, model pruning, pipeline training, and rendering.
  • Item
    A Multimodal Dataset for Dialogue Intent Recognition through Human Movement and Nonverbal Cues
    (The Eurographics Association, 2025) Lin, Shu-Wei; Zhang, Jia-Xiang; Lu, Jun-Fu Lin; Huang, Yi-Jheng; Zhang, Junpo; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper presents a multimodal dataset designed to advance dialogue intent recognition through skeleton-based representations and temporal human movement features. Rather than proposing a new model, our objective is to provide a high-quality, annotated dataset that captures subtle nonverbal cues preceding human speech and interaction. The dataset includes skeletal joint coordinates, facial orientation, and contextual object data (e.g., microphone positions), collected from diverse participants across varied conversational scenarios. In the future research, we will benchmark three types of learning methods and offer comparative insights. The benchmark three types of learning methods will be handcrafted feature models, sequence models (LSTM), and graph-based models (GCN). This resource aims to facilitate the development of more natural, sensor-free, and data-driven human-computer interaction systems by providing a robust foundation for training and evaluation.
  • Item
    Body-Scale-Invariant Motion Embedding for Motion Similarity
    (The Eurographics Association, 2025) Du, Xian; Quan, Chuyan; Yu, Ri; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Accurate measurement of motion similarity is crucial for applications in healthcare, rehabilitation, sports analysis, and human- computer interaction. However, existing Human Pose Estimation (HPE) approaches often conflate motion dynamics with anatomical variations, leading to body-scale-dependent similarity assessments. We propose a framework for learning bodyscale- invariant motion embeddings directly from RGB videos. Leveraging diverse 3D character animations with varied skeletal proportions, we generate standardized motion data and train the SAME model to capture temporal dynamics independent of body size. Our approach enables robust cross-character motion similarity evaluation. Experimental results show that the method effectively decouples kinematic patterns from structural differences, outperforming scale-sensitive baselines. Key contributions include: (1) a scalable motion data processing pipeline; (2) a learning-based body-scale-invariant embedding method; and (3) validation of motion similarity assessment independent of anatomy.
  • Item
    WotaBeats: Avatar-based Rhythm Interaction Applied Wotagei in Virtual Reality Experience
    (The Eurographics Association, 2025) Lai, Kalin Guanlun; Wang, Guan-Wen; Ting, Yi; Wang, Heng-Hao; Lai, Hsuan-Tung; Chang, Zhe-Cheng; Chiang, Po-Hung; Pan, Tse-Yu; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This paper presents a novel interactive system that combines Wotagei culture and virtual reality (VR), with the aim of providing an immersive training platform for beginners and experienced dancers. Despite the growing popularity of Wotagei, current training resources are limited. To address this gap, the system integrates intuitive gaming elements from popular rhythm games, motion capture technology, and interactive virtual environments, facilitating effective learning. By leveraging VR's immersive capabilities, the system significantly enhances user engagement, providing a culturally authentic and accessible platform for mastering Wotagei.
  • Item
    From Steps to Verses: Following the Shared Journey of Language and the Body Through Wearable Technology
    (The Eurographics Association, 2025) Yi-Wen, Huang; Tsun-Hung, Tsai; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This study investigates a creative practice that uses bodily movement as linguistic input, departing from the efficiency-driven logic of traditional typing. The ''Keyboard Shoes'' embed mechanical switches in the soles, converting walking into letter inputs that map to Chinese characters for acrostic poem generation. Inspired by the legend of ''composing a poem within seven steps,'' the work reframes walking as poetic input, forging new links between language and motion. A minimal algorithm preserves ambiguity and openness, prioritizing the generative process over semantic control. This approach reimagines the relationship between language, writing, and the body through wearable technology.
  • Item
    ServeSense: Interactive VR Tennis Serve Training System Enhanced with Haptic Feedback
    (The Eurographics Association, 2025) Tsao, Chi; Shan, Ryan; Yu, Neng-Hao; Pan, Tse-Yu; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    Tennis serves are a crucial aspect of the sport, often dictating the rhythm of a match and providing players with a competitive edge. While previous studies have explored the use of virtual reality (VR) to enhance tennis performance, they have largely overlooked the significance of tennis serves. To address this gap, the proposed ServeSense integrates gaming elements with Arduino hardware to enhance realism through haptic feedback. Users train in a gamified, fantasy environment, engaging in immersive and interactive tennis serve challenges. The system is designed to motivate user engagement while improving training efficiency.
  • Item
    Exploring Perceptual Homogenization through a VR-Based AI Narrative
    (The Eurographics Association, 2025) Kao, Bing-Chen; Tsai, Tsun-Hung; Christie, Marc; Han, Ping-Hsuan; Lin, Shih-Syun; Pietroni, Nico; Schneider, Teseo; Tsai, Hsin-Ruey; Wang, Yu-Shuen; Zhang, Eugene
    This research explores how the drive for cognitive efficiency in Artificial Intelligence (AI) may contribute to the homogenization of sensory experiences. We present Abstract.exe, a Virtual Reality (VR) installation designed as a critical medium for this inquiry. The experience places participants in a detailed virtual forest where their exploration triggers an AI-driven ''simplification'' of the world. Visuals, models, and lighting progressively degrade, aiming to transform the 3D scene into abstract 2D color fields. This work attempts to translate the abstract logic of AI-driven summarization into a tangible, immersive experience. This paper outlines the concept and technical implementation in Unreal Engine 5 (UE5), which utilizes a Procedural Content Generation (PCG) framework. Abstract.exe is intended as both an artistic inquiry and a cautionary exploration of how we might preserve experiential richness in an algorithmically influenced world.