Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts
No full textReconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. This reassembly problem requires understanding the attributes of individual pieces and establishing matches between different pieces. Many approaches also model priors of the underlying complete object. Existing approaches are tightly connected problems of shape segmentation, shape matching, and learning shape priors. We provide existing algorithms in this context and emphasize their similarities and differences to general-purpose approaches. We also survey the trends from early procedural approaches to more recent deep learning approaches. In addition to algorithms, this survey will also describe existing datasets, open-source software packages, and applications. To the best of our knowledge, this is the first comprehensive survey on this topic in computer graphics.Computer Graphics ForumState of the Art Reports442sta
Exploring the Relationship between Personality and Difficulty Adaptation to Enhance Enjoyment and Self-Efficacy in a VR Game
No full textIt is known that a user's personality influences the genres of games they prefer, but the relationship between personality and game mechanics has been less investigated. However, discovering such relationships is important for understanding how adjusting game difficulty based on users' personalities can enhance their intrinsic motivation. This paper investigates the relationship between Big Five personality traits and difficulty adaptation methods constructed using static difficulty curves in a VR Kendama game. The results revealed statistically correlation trends between specific personality traits within the Big Five factors and indicators of intrinsic motivation-namely, enjoyment and self-efficacy-across three different difficulty adaptation methods. This suggests that by utilizing the derived correlations, appropriately selecting difficulty adaptation methods when users with specific personality traits play the game could simultaneously enhance their enjoyment and self-efficacy.ICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments - Posters and DemosPosters and Demo
Algorithms in Geometric Deep learning and 3D AI: Theoretical Survey
No full textThe study of shapes and geometric representations has long been central to Artificial Intelligence (AI). Early neural networks were limited to Euclidean domains such as images and sequences. The first extensions to non-Euclidean structures appeared in the 1990s and 2000s with recursive neural networks for hierarchical data and random walk-based graph methods. A major step forward came with spectral graph convolutional networks, which introduced convolution in the Fourier domain but faced scalability issues. Spatial methods later enabled more practical graph neural networks (GNNs). In parallel, 3D vision advanced with point cloud models such as PointNet and DGCNN, and mesh-based approaches like Geodesic CNN and MeshCNN, driving progress in classification, segmentation, and reconstruction. As algorithms in geometric deep learning and 3D AI expand, the field has grown both powerful and complex. This paper categorizes major algorithmic families, surveys key datasets across Euclidean and non-Euclidean domains, and highlights emerging advances and open research challenges.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceLearning-based Algorithm
Uncertainty-Aware Gaussian Splatting with View-Dependent Regularization for High-Fidelity 3D Reconstruction
No full text3D Gaussian Splatting (3DGS) has emerged as a groundbreaking paradigm for explicit scene representation, achieving photorealistic novel view synthesis with real-time rendering capabilities. However, reconstructing geometrically consistent and accurate surfaces under complex real-world scenarios remains a critical challenge. Current 3DGS frameworks primarily rely on photometric loss optimization, which often results in multi-view geometric inconsistencies and inadequate handling of texture-less regions due to two inherent limitations: 1) the absence of explicit geometric constraints during Gaussian parameter optimization, and 2) the lack of effective mechanisms to resolve multi-view geometric ambiguities. To address these challenges, we propose Uncertainty-Aware Gaussian Splatting (UA-GS), a novel framework that integrates geometric priors with view-dependent uncertainty modeling to explicitly capture and resolve multi-view inconsistencies. For efficient optimization of Gaussian attributes, our approach introduces a spherical harmonics-based uncertainty representation that dynamically models view-dependent geometric variations. Building on this framework, we further design uncertainty-aware optimization strategies. Extensive experiments on real-world and synthetic benchmarks demonstrate that our method significantly outperforms state-of-the-art 3DGS-based approaches in geometric accuracy while retaining competitive rendering quality. Code and data will be made available soon.Eurographics Symposium on RenderingGaussian
Neural Path Guiding with Distribution Factorization
No full textIn this paper, we present a neural path guiding method to aid with Monte Carlo (MC) integration in rendering. Existing neural methods utilize distribution representations that are either fast or expressive, but not both. We propose a simple, but effective, representation that is sufficiently expressive and reasonably fast. Specifically, we break down the 2D distribution over the directional domain into two 1D probability distribution functions (PDF). We propose to model each 1D PDF using a neural network that estimates the distribution at a set of discrete coordinates. The PDF at an arbitrary location can then be evaluated and sampled through interpolation. To train the network, we maximize the similarity of the learned and target distributions. To reduce the variance of the gradient during optimizations and estimate the normalization factor, we propose to cache the incoming radiance using an additional network. Through extensive experiments, we demonstrate that our approach is better than the existing methods, particularly in challenging scenes with complex light transport.Eurographics Symposium on RenderingSampling and Guidin
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
No full textWe demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Common diffusion models are not HDR as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called ''exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. To this end, we introduce a brackets consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share. We demonstrate HDR versions of state-of-the-art unconditional and conditional as well as restoration-type (LDR2HDR) generative modeling.Computer Graphics ForumFix it in Post: Image and Video Synthesis and Analysis44
Multi-Density Woodcock Tracking: Efficient & High-Quality Rendering for Multi-Channel Volumes
No full textVolume rendering techniques for scientific visualization have increasingly transitioned toward Monte Carlo (MC) methods in recent years due to their flexibility and robustness. However, their application in multi-channel visualization remains underexplored. Traditional compositing-based approaches often employ arbitrary color blending functions, which lack a physical basis and can obscure data interpretation. We introduce multi-density Woodcock tracking, a simple and flexible extension of Woodcock tracking for multi-channel volume rendering that leverages the strengths of Monte Carlo methods to generate high-fidelity visuals. Our method offers a physically grounded solution for inter-channel color blending and eliminates the need for arbitrary blending functions. We also propose a unified blending modality by generalizing Woodcock's distance tracking method, facilitating seamless integration of alternative blending functions from prior works. Through evaluation across diverse datasets, we demonstrate that our approach maintains real-time interactivity while achieving high-quality visuals by accumulating frames over time.Eurographics Symposium on Parallel Graphics and VisualizationPaper
Quantized FCA: Efficient Zero-Shot Texture Anomaly Detection
No full textZero-shot anomaly localization is a rising field in computer vision research, with important progress in recent years. This work focuses on the problem of detecting and localizing anomalies in textures, where anomalies can be defined as the regions that deviate from the overall statistics, violating the stationarity assumption. The main limitation of existing methods is their high running time, making them impractical for deployment in real-world scenarios, such as assembly line monitoring. We propose a real-time method, named QFCA, which implements a quantized version of the feature correspondence analysis (FCA) algorithm. By carefully adapting the patch statistics comparison to work on histograms of quantized values, we obtain a 10× speedup with little to no loss in accuracy. Moreover, we introduce a feature preprocessing step based on principal component analysis, which enhances the contrast between normal and anomalous features, improving the detection precision on complex textures. Our method is thoroughly evaluated against prior art, comparing favorably with existing methods. Project page: reality.tf.fau.de/pub/ardelean2025quantized.html.Vision, Modeling, and VisualizationImaging and Image Processin
Viewpoint Optimization for 3D Graph Drawings
No full textGraph drawings using a node-link metaphor and straight edges are widely used to represent and understand relational data. While such drawings are typically created in 2D, 3D representations have also gained popularity. When exploring 3D drawings, finding viewpoints that help understanding the graph's structure is crucial. Finding good viewpoints also allows using the 3D drawings to generate good 2D graph drawings. In this work, we tackle the problem of automatically finding high-quality viewpoints for 3D graph drawings. We propose and evaluate strategies based on sampling, gradient descent, and evolutionary-inspired meta-heuristics. Our results show that most strategies quickly converge to high-quality viewpoints within a few dozen function evaluations, with meta-heuristic approaches showing robust performance regardless of the quality metric.Computer Graphics ForumNetworks and Structure
Neural Face Skinning for Mesh-agnostic Facial Expression Cloning
No full textAccurately retargeting facial expressions to a face mesh while enabling manipulation is a key challenge in facial animation retargeting. Recent deep-learning methods address this by encoding facial expressions into a global latent code, but they often fail to capture fine-grained details in local regions. While some methods improve local accuracy by transferring deformations locally, this often complicates overall control of the facial expression. To address this, we propose a method that combines the strengths of both global and local deformation models. Our approach enables intuitive control and detailed expression cloning across diverse face meshes, regardless of their underlying structures. The core idea is to localize the influence of the global latent code on the target mesh. Our model learns to predict skinning weights for each vertex of the target face mesh through indirect supervision from predefined segmentation labels. These predicted weights localize the global latent code, enabling precise and region-specific deformations even for meshes with unseen shapes. We supervise the latent code using Facial Action Coding System (FACS)-based blendshapes to ensure interpretability and allow straightforward editing of the generated animation. Through extensive experiments, we demonstrate improved performance over state-of-the-art methods in terms of expression fidelity, deformation transfer accuracy, and adaptability across diverse mesh structures.Computer Graphics ForumFace-First for Digital Avatars44