773 results
Search Results
Now showing 1 - 10 of 773
Item DeepTex: Deep Learning-Based Texturing of Image-Based 3D Reconstructions(The Eurographics Association, 2024) Neumann, Kai Alexander; Santos, Pedro; Fellner, Dieter W.; Corsini, Massimiliano; Ferdani, Daniele; Kuijper, Arjan; Kutlu, HasanImage-based 3D reconstruction is a commonly used technique for measuring the geometry and color of objects or scenes based on images. While the geometry reconstruction of state-of-the-art approaches is mostly robust against varying lighting conditions and outliers, these pose a significant challenge for calculating an accurate texture map. This work proposes a deep-learning based texturing approach called ''DeepTex'' that uses a custom learned blending method on top of a traditional mosaic-based texturing approach. The model was trained using a custom synthetic data generation workflow and showed a significantly increased accuracy when generating textures in the presence of outliers and non-uniform lighting.Item Show Me Similar Nodes: The Similarity Lens for Multivariate Graphs(The Eurographics Association, 2024) Tominski, Christian; Berger, Philip; Tominski, Christian; Waldner, Manuela; Wang, BeiNode-link diagrams with topology-driven layouts are effective tools for visually exploring the structure of graphs. When exploring multivariate graphs, a frequent analytical question is to ask which graph nodes are similar in terms of their multivariate attribute values. Answering this question would usually involve switching to an attribute-driven layout or a different visual representation altogether. However, such context switches may ensue additional cognitive costs and hinder the fluent exploration of the graph. In this paper, we present an interactive lens technique, called the similarity lens. It avoids global view changes by dynamically injecting a local attribute-driven layout into an otherwise topology-driven layout. Given a focus node of interest in the center of the lens, dissimilar nodes are pushed out of the lens and similar nodes are pulled inward, with the most similar nodes closest to the focus node. This dynamic layout adaptation facilitates comparison tasks on a local level without disturbing the user's overall mental map of the graph topology too much. We demonstrate the utility of our approach by exploring a real-world multivariate graph of soccer players.Item Seamless and Aligned Texture Optimization for 3D Reconstruction(The Eurographics Association and John Wiley & Sons Ltd., 2024) Wang, Lei; Ge, Linlin; Zhang, Qitong; Feng, Jieqing; Chen, Renjie; Ritschel, Tobias; Whiting, EmilyRestoring the appearance of the model is a crucial step for achieving realistic 3D reconstruction. High-fidelity textures can also conceal some geometric defects. Since the estimated camera parameters and reconstructed geometry usually contain errors, subsequent texture mapping often suffers from undesirable visual artifacts such as blurring, ghosting, and visual seams. In particular, significant misalignment between the reconstructed model and the registered images will lead to texturing the mesh with inconsistent image regions. However, eliminating various artifacts to generate high-quality textures remains a challenge. In this paper, we address this issue by designing a texture optimization method to generate seamless and aligned textures for 3D reconstruction. The main idea is to detect misalignment regions between images and geometry and exclude them from texture mapping. To handle the texture holes caused by these excluded regions, a cross-patch texture hole-filling method is proposed, which can also synthesize plausible textures for invisible faces. Moreover, for better stitching of the textures from different views, an improved camera pose optimization is present by introducing color adjustment and boundary point sampling. Experimental results show that the proposed method can eliminate the artifacts caused by inaccurate input data robustly and produce highquality texture results compared with state-of-the-art methods.Item Towards Environment- and Task-Independent Locomotion Prediction for Haptic VR(The Eurographics Association, 2024) Varzandeh, Shokoofeh; Vasylevska, Khrystyna; Vonach, Emanuel; Kaufmann, Hannes; Hasegawa, Shoichi; Sakata, Nobuchika; Sundstedt, VeronicaThe use of robots presenting physical props has significantly enhanced the haptic experience in virtual reality. Autonomous mobile robots made haptic interaction in large walkable virtual environments feasible but brought new challenges. For effective operation, a mobile robot must not only track the user but also predict her future position for the next several seconds to be able to plan and navigate in the common space safely and timely. This paper presents a novel environment- and taskindependent concept for locomotion-based prediction of the user position within a chosen range. Our approach supports the dynamic placement of haptic content with minimum restrictions. We validate it based on a real use case by making predictions within a range of 2 m to 4 m or 2 s to 5 s. We also discuss the adaptation to arbitrary space sizes and configurations with minimal real data collection. Finally, we suggest optimal utilization strategies and discuss the limitations of our approach.Item Polygon Laplacian Made Robust(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024)Item CEIG 2024: Frontmatter(The Eurographics Association, 2024) Marco, Julio; Patow, Gustavo; Marco, Julio; Patow, GustavoItem Enhancing Medical Diagnosis and Treatment Planning through Automated Acquisition and Classification of Bone Fracture Patterns(The Eurographics Association, 2024) Pérez-Cano, Francisco Daniel; Parra-Cabrera, Gema; Camacho-García, Rubén; Jiménez, Juan José; Marco, Julio; Patow, GustavoThe extraction of the main features of a fractured bone area enables subsequent virtual reproduction for bone simulations. Exploring the fracture zone for other applications remains largely unexplored in current research. Recreating and analyzing fracture patterns has direct applications in medical training programs for traumatologists, automatic bone fracture reduction algorithms, and diagnostics. Furthermore, pattern classification aids in establishing treatment guidelines that specialists can follow during the surgical process. This paper focuses on the process of obtaining an accurate representation of bone fractures, starting with computed tomography scans, and subsequently classifying these patterns using a convolutional neural network. The proposed methodology aims to streamline the extraction and classification of fractures from clinical cases, contributing to enhanced diagnosis and medical simulation applications.Item ETBHD‐HMF: A Hierarchical Multimodal Fusion Architecture for Enhanced Text‐Based Hair Design(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) He, Rong; Jiao, Ge; Li, Chen; Alliez, Pierre; Wimmer, MichaelText‐based hair design (TBHD) represents an innovative approach that utilizes text instructions for crafting hairstyle and colour, renowned for its flexibility and scalability. However, enhancing TBHD algorithms to improve generation quality and editing accuracy remains a current research difficulty. One important reason is that existing models fall short in alignment and fusion designs. Therefore, we propose a new layered multimodal fusion network called ETBHD‐HMF, which decouples the input image and hair text information into layered hair colour and hairstyle representations. Within this network, the channel enhancement separation (CES) module is proposed to enhance important signals and suppress noise for text representation obtained from CLIP, thus improving generation quality. Based on this, we develop the weighted mapping fusion (WMF) sub‐networks for hair colour and hairstyle. This sub‐network applies the mapper operations to input image and text representations, acquiring joint information. The WMF then selectively merges image representation and joint information from various style layers using weighted operations, ultimately achieving fine‐grained hairstyle designs. Additionally, to enhance editing accuracy and quality, we design a modality alignment loss to refine and optimize the information transmission and integration of the network. The experimental results of applying the network to the CelebA‐HQ dataset demonstrate that our proposed model exhibits superior overall performance in terms of generation quality, visual realism, and editing accuracy. ETBHD‐HMF (27.8 PSNR, 0.864 IDS) outperformed HairCLIP (26.9 PSNR, 0.828 IDS), with a 3% higher PSNR and a 4% higher IDS.Item Curved Three-Director Cosserat Shells with Strong Coupling(The Eurographics Association and John Wiley & Sons Ltd., 2024) Löschner, Fabian; Fernández-Fernández, José Antonio; Jeske, Stefan Rhys; Bender, Jan; Skouras, Melina; Wang, HeContinuum-based shell models are an established approach for the simulation of thin deformables in computer graphics. However, existing research in physically-based animation is mostly focused on shear-rigid Kirchhoff-Love shells. In this work we explore three-director Cosserat (micropolar) shells which introduce additional rotational degrees of freedom. This microrotation field models transverse shearing and in-plane drilling rotations. We propose an incremental potential formulation of the Cosserat shell dynamics which allows for strong coupling with frictional contact and other physical systems. We evaluate a corresponding finite element discretization for non-planar shells using second-order elements which alleviates shear-locking and permits simulation of curved geometries. Our formulation and the discretization, in particular of the rotational degrees of freedom, is designed to integrate well with typical simulation approaches in physically-based animation. While the discretization of the rotations requires some care, we demonstrate that they do not pose significant numerical challenges in Newton's method. In our experiments we also show that the codimensional shell model is consistent with the respective three-dimensional model. We qualitatively compare our formulation with Kirchhoff-Love shells and demonstrate intriguing use cases for the additional modes of control over dynamic deformations offered by the Cosserat model such as directly prescribing rotations or angular velocities and influencing the shell's curvature.Item EuroVis 2024 Short Papers: Frontmatter(The Eurographics Association, 2024) Tominski, Christian; Waldner, Manuela; Wang, Bei; Tominski, Christian; Waldner, Manuela; Wang, Bei