Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Cage-based Deformation of Field Functions
No full textImplicit geometry is a popular representation for shape modelling. It provides several interesting properties, such as infinite resolution, continuity and smooth blending. However, implicit surfaces are difficult to deform as deformations need to be invertible. They are in general restricted to linear representations or more advanced translation-based deformations. We propose a method that adapts cage-based deformation to implicit surfaces while handling self-intersections in the deformed space.Eurographics 2025 - PostersPoster
Structured Pattern Expansion with Diffusion Models
No full textRecent advances in diffusion models have significantly improved the synthesis of materials, textures, and 3D shapes. By conditioning these models on text or images, users can guide the generation, reducing the time required to create digital assets. In this paper, we address the synthesis of structured, stationary patterns, where diffusion models are generally less reliable and, more importantly, less controllable. Our approach leverages the generative capabilities of diffusion models specifically adapted to the pattern domain. It enables users to exercise direct control over the synthesis by expanding a partially hand-drawn pattern into a larger design while preserving the structure and details of the input. To enhance pattern quality, we fine-tune an image-pretrained diffusion model on structured patterns using Low-Rank Adaptation (LoRA), apply a noise rolling technique to ensure tileability, and utilize a patch-based approach to facilitate the generation of large-scale assets. We demonstrate the effectiveness of our method through a comprehensive set of experiments, showing that it outperforms existing models in generating diverse, consistent patterns that respond directly to user input. Code will be released at publication time at: https://github.com/marzia-riso/structured_pattern_expansion.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceLearning-based Algorithm
HPRO: Direct Visibility of Point Clouds for Optimization
No full textGiven a point cloud, which is assumed to be a sampling of a continuous surface, and a viewpoint, which points are visible from that viewpoint? Since points do not occlude each other, the real question is which points would be visible if the surface they were sampled from were known. While an existing approximation method addresses this problem, it is unsuitable for use in optimization processes or learning models due to its lack of differentiability. To overcome this limitation, the paper introduces a novel differentiable approximation method. It is based on identifying the extreme points of a point set in a differentiable manner. This approach can be effectively integrated into optimization algorithms or used as a layer in neural networks, allowing for the computation and utilization of visible points in various tasks, such as optimal viewpoint selection. The paper also provides theoretical proofs of the operator's correctness in the limit, further validating its effectiveness. The code is available at https://github.com/sagikatz/HPROComputer Graphics ForumThe Shape of Rendering44
ArtifactVM: Exploring Culturally Meaningful Presentations and User Interactions in Virtual Museums
No full textVirtual Museums (VMs) serve as an extension of physical museums, delivering content in digital formats. Virtual Reality (VR) technologies afford the creation of interactive virtual museum experiences with 3D artifacts, enhancing cultural dissemination by narratives based on historical artifacts for educational and entertainment purposes. However, there are notable gaps in exploring the ways to interact with virtual artifacts in VMs. In this work, we conducted workshop studies with non-expert audiences and interviewed domain experts to gather insights into 3D artifacts presentation in VMs. In addition, we investigated the digital affordances of historical artifacts in VMs and discussed opportunities for interaction design. The results provide design guidelines for the forms of presentation and outline interaction possibilities. Our findings provide insights into future forms of content curation and artifact interaction in virtual museums.Digital HeritagePhygital Worlds and XR in Cultural Heritag
Adaptive Multi-view Radiance Caching for Heterogeneous Participating Media
No full textAchieving lifelike atmospheric effects, such as fog, is essential in creating immersive environments and poses a formidable challenge in real-time rendering. Highly realistic rendering of complex lighting interacting with dynamic fog can be very resourceintensive, due to light bouncing through a complex participating media multiple times. We propose an approach that uses a multi-layered spherical harmonics probe grid to share computations temporarily. In addition, this world-space storage enables the sharing of radiance data between multiple viewers. In the context of cloud rendering this means faster rendering and a significant enhancement in overall rendering quality with efficient resource utilization.Computer Graphics ForumLighting the Way: Scattering and Transport in Rendering44
Social Dimensions in Content Creation for Games: A Systematic Review of Fairness, Social Bias, and Diversity in Computational Character and Environment Generation
No full textComputational content generation increasingly shapes digital games, visual computing, and interactive environments, automating the creation of characters and environments. However, these systems also raise complex challenges related to fairness, social bias, and representational diversity. We present a systematic literature review of 37 recent studies addressing fairness-aware computational content generation across character creation, face modeling, and procedural environments. We analyze both algorithmic strategies - including deep learning, reinforcement learning, generative adversarial networks, and optimization - as well as design-oriented frameworks such as behavioral, participatory, and cultural methods. Our review reveals substantial conceptual fragmentation in how fairness, social bias, and diversity are defined, measured, and operationalized across domains. While several metrics (e.g., statistical parity, balanced accuracy, generative diversity scores) are applied, standardized computational frameworks and large-scale auditing tools remain largely absent. We conclude by outlining key research challenges, including metric standardization, scalable fairness, social bias, and diversity auditing, cross-cultural dataset development, and interdisciplinary collaboration, to advance aware content generation in games.Computer Graphics and Visual Computing (CGVC)Game
Tasks and Visual Abstractions for 3D Chromatin Representation
No full textThe spatial organization of chromatin fiber directly influences its function. However, the high visual complexity of chromatin spatial models makes the understanding of the structure extremely challenging. Therefore, genomic researchers still primarily rely on indirect analysis of chromatin through 2D views, missing the advantages that 3D visualization can offer. In this paper, we first analyze the task space of genomic research and identify biological domain tasks that can benefit from dedicated spatial representations. We organize these tasks into four categories: tasks related to structural features, additional meta-data, structural relationships, and comparative tasks. We analyze these tasks in terms of their complexity, co-dependence, and potential benefits of 3D-based solutions. Secondly, we present four newly designed visual representations of chromatin 3D structure, focused on enhancing the understanding of structural features and solving relationships tasks. These include the hierarchical nature of spatial chromatin sub-units, their visual abstractions, spatial interactions, and a cumulative representation of chromatin dynamic behavior. We also include feedback from four domain researchers and discuss future steps necessary to make spatial representations valid and valuable part of genomic research.Computer Graphics ForumNetworks and Structure
Learning Climbing Controllers for Physics‐Based Characters
No full textDespite the growing demand for capturing diverse motions, collecting climbing motion data remains challenging due to difficulties in tracking obscured markers and scanning climbing structures. Additionally, preparing varied routes further adds to the complexities of the data collection process. To address these challenges, this paper introduces a physics‐based climbing controller for synthesizing climbing motions. The proposed method consists of two learning stages. In the first stage, a hanging policy is trained to naturally grasp holds. This policy is then used to generate a dataset containing hold positions, postures, and grip states, forming favourable initial poses. In the second stage, a climbing policy is trained using this dataset to perform actual climbing movements. The episode begins in a state close to the reference climbing motion, enabling the exploration of more natural climbing style states. This policy enables the character to reach the target position while utilizing its limbs more evenly. The experiments demonstrate that the proposed method effectively identifies good climbing postures and enhances limb coordination across environments with varying slopes and hold patterns.Computer Graphics ForumOriginal Article44
