Pacific Graphics 2019 - Symposium Proceedings
Korea University, Seoul, Korea
October 14 – 17, 2019
(for Short Papers see PG 2019 - Short Papers)
Color and Image
Succinct Palette and Color Model Generation and Manipulation Using Hierarchical Representation
An Improved Geometric Approach for Palette-based Image Decomposition and Recoloring
Generic Interactive Pixel-level Image Editing
Parallel Generation and Visualization of Bacterial Genome Structures
Lines and Sketches
Learning to Trace: Expressive Line Drawing Generation from Photographs
Deep Line Drawing Vectorization via Line Subdivision and Topology Reconstruction
Pencil Drawing Video Rendering Using Convolutional Networks
Active Scene Understanding via Online Semantic Reconstruction
Surface Fairing towards Regular Principal Curvature Line Networks
Subdivision Schemes for Quadrilateral Meshes with the Least Polar Artifact in Extraordinary Regions
Imitating Popular Photos to Select Views for an Indoor Scene
Scale-adaptive Structure-preserving Texture Filtering
Rain Wiper: An Incremental RandomlyWired Network for Single Image Deraining
Field-aligned Quadrangulation for Image Vectorization
Learning Explicit Smoothing Kernels for Joint Image Filtering
Perception and Visualization
ManyLands: A Journey Across 4D Phase Space of Trajectories
Inertia-based Fast Vectorization of Line Drawings
Generating 3D Faces using Multi-column Graph Convolutional Networks
Figure Skating Simulation from Video
Towards Robust Direction Invariance in Character Animation
Dual Illumination Estimation for Robust Exposure Correction
Specular Highlight Removal for Real-world Images
Light Field Video Compression and Real Time Rendering
Naturalness-Preserving Image Tone Enhancement Using Generative Adversarial Networks
Voxels and Polycubes
Practical Foldover-Free Volumetric Mapping Construction
Computing Surface PolyCube-Maps by Constrained Voxelization
Polycube Shape Space
Compacting Voxelized Polyhedra via Tree Stacking
Multi-View and VR
Pyramid Multi-View Stereo with Local Consistency
Automatic Modeling of Cluttered Multi-room Floor Plans From Panoramic Images
A Generalized Cubemap for Encoding 360° VR Videos using Polynomial Approximation
Interactive Curation of Datasets for Training and Refining Generative Models
Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions
HidingGAN: High Capacity Information Hiding with Generative Adversarial Network
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
Rendering and Sampling
Visibility-Aware Progressive Farthest Point Sampling on the GPU
Unsupervised Dense Light Field Reconstruction with Occlusion Awareness
Seamless Mipmap Filtering for Dual Paraboloid Maps
Real-time Indirect Illumination of Emissive Inhomogeneous Volumes using Layered Polygonal Area Lights
Images and Learning
A Unified Neural Network for Panoptic Segmentation
Style Mixer: Semantic-aware Multi-Style Transfer Network
A Color-Pair Based Approach for Accurate Color Harmony Estimation
Cloth and Fluid
Distribution Update of Deformable Patches for Texture Synthesis on the Free Surface of Fluids
A Rigging-Skinning Scheme to Control Fluid Simulation
High Dynamic Range Point Clouds for Real-Time Relighting
Offline Deep Importance Sampling for Monte Carlo Path Tracing
Image Based Rendering
Deep Video-Based Performance Synthesis from Sparse Multi-View Capture
Appearance Flow Completion for Novel View Synthesis
FontRNN: Generating Large-scale Chinese Fonts via Recurrent Neural Network
Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image
Mesh Defiltering via Cascaded Geometry Recovery
Topology Preserving Simplification of Medial Axes in 3D Models
Intrinsic Symmetry Detection on 3D Models with Skeleton-guided Combination of Extrinsic Symmetries
Single-View Modeling of Layered Origami with Plausible Outer Shape
Image and Video Editing
Image Composition of Partially Occluded Objects
A PatchMatch-based Approach for Matte Propagation in Videos
Wavelet Flow: Optical Flow Guided Wavelet Facial Image Fusion
ShutterApp: Spatio-temporal Exposure Control for Videos
Surface and Texture
Selecting Texture Resolution Using a Task-specific Visibility Metric
Global Texture Mapping for Dynamic Objects
Discrete Calabi Flow: A Unified Conformal Parameterization Method
Reliable Rolling-guided Point Normal Filtering for Surface Texture Removal
Rendering and Lighting
Lighting Layout Optimization for 3D Indoor Scenes
A Stationary SVBRDF Material Modeling Method Based on Discrete Microsurface
Anisotropic Surface Remeshing without Obtuse Angles
RodSteward: A Design-to-Assembly System for Fabrication using 3D-Printed Joints and Precision-Cut Rods
Learning Style Compatibility Between Objects in a Real-World 3D Asset Database
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Large 3D asset databases are critical for designing virtual worlds, and using them effectively requires techniques for efficient querying and navigation. One important form of query is search by style compatibility: given ...
RodSteward: A Design-to-Assembly System for Fabrication using 3D-Printed Joints and Precision-Cut Rods (The Eurographics Association and John Wiley & Sons Ltd., 2019)We present RodSteward, a design-to-assembly system for creating furniture-scale structures composed of 3D-printed joints and precision-cut rods. The RodSteward systems consists of: RSDesigner, a fabrication-aware design ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Microfacet theory is commonly used to build reflectance models for surfaces. While traditional microfacet-based models assume that the distribution of a surface's microstructure is continuous, recent studies indicate that ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)We present a novel anisotropic surface remeshing method that can efficiently eliminate obtuse angles. Unlike previous work that can only suppress obtuse angles with expensive resampling and Lloyd-type iterations, our method ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)As the number of models for 3D indoor scenes are increasing rapidly, methods for generating the lighting layout have also become increasingly important. This paper presents a novel method that creates optimal placements ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Semantic surface decomposition (SSD) facilitates various geometry processing and product re-design tasks. Filter-based techniques are meaningful and widely used to achieve the SSD, which however often leads to surface ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Conformal parameterization for surfaces into various parameter domains is a fundamental task in computer graphics. Prior research on discrete Ricci flow provided us with promising inspirations from methods derived via ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)We propose a novel framework to generate a global texture atlas for a deforming geometry. Our approach distinguishes from prior arts in two aspects. First, instead of generating a texture map for each timestamp to color a ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)In real-time rendering, the appearance of scenes is greatly affected by the quality and resolution of the textures used for image synthesis. At the same time, the size of textures determines the performance and the memory ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)A camera's shutter controls the incoming light that is reaching the camera sensor. Different shutters lead to wildly different results, and are often used as a tool in movies for artistic purpose, e.g., they can indirectly ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Estimating the correspondence between the images using optical flow is the key component for image fusion, however, computing optical flow between a pair of facial images including backgrounds is challenging due to large ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Despite considerable advances in natural image matting over the last decades, video matting still remains a difficult problem. The main challenges faced by existing methods are the large amount of user input required, and ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Image composition extracts the content of interest (COI) from a source image and blends it into a target image to generate a new image. In the majority of existing works, the COI is manually extracted and then overlaid on ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Modeling 3D origami pieces using conventional software is laborious due to the geometric constraints imposed by the complicated layered structure. Targeting origami models used in visual content such as CG illustrations ...
Intrinsic Symmetry Detection on 3D Models with Skeleton-guided Combination of Extrinsic Symmetries (The Eurographics Association and John Wiley & Sons Ltd., 2019)The existing methods for intrinsic symmetry detection on 3D models always need complex measures such as geodesic distances for describing intrinsic geometry and statistical computation for finding non-rigid transformations ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)We propose an efficient method for topology-preserving simplification of medial axes of 3D models. Existing methods either cannot preserve the topology during medial axes simplification or have the problem of being ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)This paper addresses the nontraditional but practically meaningful reversibility problem of mesh filtering. This reverse-filtering approach (termed a DeFilter) seeks to recover the geometry of a set of filtered meshes to ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Image metrics predict the perceived per-pixel difference between a reference image and its degraded (e. g., re-rendered) version. In several important applications, the reference image is not available and image metrics ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Despite the recent impressive development of deep neural networks, using deep learning based methods to generate largescale Chinese fonts is still a rather challenging task due to the huge number of intricate Chinese glyphs, ...
(The Eurographics Association and John Wiley & Sons Ltd., 2019)Novel view synthesis from sparse and unstructured input views faces challenges like the difficulty with dense 3D reconstruction and large occlusion. This paper addresses these problems by estimating proper appearance flows ...