Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
ACM/EG Expressive Symposium 2025 Posters and Demos: Frontmatter
No full textACM/EG Expressive Symposium - Eurographics Workshop on Intelligent Cinematography and Editing 2025 (Posters and Demos
Enhancing Cultural Heritage with Generative AI: A Comparative Framework for the Evaluation of 3D Model Accuracy and Visual Fidelity
No full textThe digitization of Cultural Heritage (CH) has become a vital tool for preservation and dissemination, with 3D reconstruction playing a key role in capturing intricate geometries and visual details of artifacts. While traditional methods like photogrammetry and laser scanning are effective, they often involve labor-intensive processes and struggle with complex material properties. Recent advancements in Generative AI (GenAI), particularly Large Reconstruction Models (LRMs) such as TRELLIS, offer promising alternatives for 3D generation. However, their application in CH remains underexplored. This paper introduces a novel comparative framework to evaluate the accuracy and visual fidelity of 3D GenAI models in the CH domain. Focusing on TRELLIS, the framework assesses single-view and multi-view 3D generation across five diverse CH scenes, employing both 2D (PSNR, SSIM, LPIPS) and 3D (Chamfer Distance, F-score, Accuracy) metrics. Results demonstrate superior performance for individual artifacts (e.g., Minareto, Greek Vase) compared to complex architectural scenes, with multi-view generation consistently outperforming single-view approaches. The study highlights the potential of GenAI for CH preservation while identifying challenges in large-scale reconstructions, paving the way for future hybrid methodologies and sparse-view optimizations.Digital HeritageAnalysing and Documenting Digitized Asset
Level-of-Detail Digitization of High Ceilings in Virtual Reality
No full textThe digitization of elevated ceilings featuring intricate 3D patterns in heritage settings presents significant challenges due to their substantial height and constrained accessibility. To address this, we propose a hybrid Level of Detail (LOD) framework that synergizes 3D Gaussian Splatting (3DGS) for rapid base reconstruction with targeted 3D scanning of regions of interest (ROIs). First, 3DGS is used to rapidly generate a low-LOD, real-time navigable model of the entire ceiling. Second, accurate 3D scanning of selected ROI captures fine surface details. This two-stage workflow significantly reduces processing time compared to full-structure scanning while preserving spatial context, enabling seamless transitions between broad-scale exploration and immersive inspection of high-fidelity fragments. Validated through a case study at the National Trust's Blickling Hall, a 17th-century gallery with a 37.5-meter-long and 4.8-meter-high ceiling, our method demonstrates scalable potential for heritage conservation, offering a blueprint for balancing reconstruction efficiency with immersive engagement.Digital HeritageDigitization Tools and Application
Panel Proposal: What is the Role of Workshops in Visualization Research?
No full textWorkshops are a core component of EuroVis and VIS conferences, providing a dedicated space for presenting innovative research, discussing new findings, and fostering community connections. Despite consistent interest in attendance, recent years have seen a troubling decline in workshop submissions, particularly since the COVID-19 pandemic. We propose a panel to explore workshops' role within the VIS community, examining factors that contribute to their success and sustainability. Key questions include identifying the elements that make workshops appealing to participants and submitters, understanding their impact on scientific careers, and assessing the potential for workshops to evolve or be integrated into larger conference formats. The goal of the panel is to develop a position paper summarizing insights from these discussions to help shape the future of workshops in the visualization and Visual Analytics field.EuroVis 2025 - Panels and TutorialsPanel
View-Dependent Deformation Fields for 2D Editing of 3D Models
No full textWe propose a method for authoring non-realistic 3D objects (represented as either 3D Gaussian Splats or meshes), that comply with 2D edits from specific viewpoints. Namely, given a 3D object, a user chooses different viewpoints and interactively deforms the object in the 2D image plane of each view. The method then produces a ''deformation field'' - an interpolation between those 2D deformations in a smooth manner as the viewpoint changes. Our core observation is that the 2D deformations do not need to be tied to an underlying object, nor share the same deformation space. We use this observation to devise a method for authoring view-dependent deformations, holding several technical contributions: first, a novel way to compositionality-blend between the 2D deformations after lifting them to 3D - this enables the user to ''stack'' the deformations similarly to layers in an editing software, each deformation operating on the results of the previous; second, a novel method to apply the 3D deformation to 3D Gaussian Splats; third, an approach to author the 2D deformations, by deforming a 2D mesh encapsulating a rendered image of the object. We show the versatility and efficacy of our method by adding cartoonish effects to objects, providing means to modify human characters, fitting 3D models to given 2D sketches and caricatures, resolving occlusions, and recreating classic non-realistic paintings as 3D models.ACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and EditingUser Guided Creative Modelin
A Summarization and Analysis of Methodologies for Creating Interactive and Lifelike Historical Characters Based on MetaHuman
No full textVirtual characters have long held promise as pedagogical tools in heritage education, particularly for creating immersive interactions with historical figures. Researchers have envisioned systems capable of emulating these figures, enabling users to engage in life-like, face-to-face dialogues over time. While technological constraints historically limited such applications, recent advancements in computational graphics and language models have now made them viable. This paper presents a frame- work for constructing interactive virtual character systems, outlining their core components through two critical dimensions: photorealism and interaction. The photorealism dimension leverages modern graphics tools to achieve high-fidelity visual rep- resentation, while the interaction dimension utilizes language models to enable socially believable and contextually responsive dialogue. We examine the necessity of each component and analyze available technological solutions with their respective trade-offs. Beyond the technical framework, we discuss potential future improvements and address ethical and practical con- cerns inherent to such systems. By synthesizing current technologies and their applicability, this work provides institutions with practical guidance for developing customized interactive systems that balance functionality with cost-efficiency.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
Riemannian Inhomogeneity and Anisotropy of Perceptual Color Space
No full textThe geometry of perceived color space is widely recognized as non-Euclidean, with the Riemannian framework commonly adopted for its analysis. However, existing evidence, such as the principle of diminishing returns, suggests that the color space may be globally non-Riemannian. In this work, we investigate the local inhomogeneities of the perceived color space under the Riemannian setting. Specifically, we evaluate the local agreement between the Riemannian model and the color-difference function. To achieve this, we perform numerical experiments to assess the accuracy of the parallelogram law, a necessary condition for the local validity of the metric tensor. Furthermore, we introduce several measures of local anisotropy to quantify directional variations in perceived color distances and compute these measures within the chromatic planes of the CIELAB color space. Our findings describe the spatial variation of Riemannian inhomogeneities and distance anisotropy, which can be used to construct adaptive spatial meshes and improve the accuracy of computations in color space. While our techniques are demonstrated on the CIELAB color model with the ΔE2000 metric, they are generalizable to the discretization of arbitrary non-Euclidean metric spaces.EuroVis 2025 - Short PapersEmpirical and Perception Studie
Seamless Collaborative Coding with Visualization
No full textCoding data is a time-consuming activity, but one that is found in many places like scientific research and public online spaces. We developed the CollaCode system to support collaborative coding for a video game dataset, leveraging visualization with ubiquitous editing for seamless transitions between editing data and analyzing coding results. CollaCode employs multiple visualizations to support different activities in the coding workflow: tagging data, analyzing coding results, and resolving disagreements. Compared to existing approaches, our system explicitly models coding iterations, allowing coders to understand tag provenance while giving more transparency to the coding process. We discuss challenges in collaborative coding settings, how our system design addresses these challenges, and opportunities we see for future work.EuroVis 2025 - Short PapersSystems and Application
Linearly Transformed Spherical Distributions for Interactive Single Scattering with Area Lights
No full textSingle scattering in scenes with participating media is challenging, especially in the presence of area lights. Considerable variance still remains, in spite of good importance sampling strategies. Analytic methods that render unshadowed surface illumination have recently gained interest since they achieve biased but noise-free plausible renderings while being computationally efficient. In this work, we extend the theory of Linearly Transformed Spherical Distributions (LTSDs) which is a well-known analytic method for surface illumination, to work with phase functions. We show that this is non-trivial, and arrive at a solution with in-depth analysis. This enables us to analytically compute in-scattered radiance, which we build on to semi-analytically render unshadowed single scattering. We ground our derivations and formulations on the Volume Rendering Equation (VRE) which paves the way for realistic renderings despite the biased nature of our method. We also formulate ratio estimators for the VRE to work in conjunction with our formulation, enabling the rendering of shadows. We extensively validate our method, analyze its characteristics and demonstrate better performance compared to Monte Carlo single-scattering.Computer Graphics ForumLighting the Way: Scattering and Transport in Rendering44
Voxels for Finite Element Analysis of Cultural Heritage objects
No full textThe paper aims at presenting a study on the integration of thermographic data with 3D models for the predictive analysis of possible degradation of wooden furniture due to changing in temperature and humidity. The project is done in collaboration with the Royal Palace of Caserta, a UNESCO site that preserve a huge, majestic collection of ancient furniture. Combining thermographic images and 3D models to proceed with thermic analysis through Finite Element Analysis (FEA) software, the aim is to identify the influence of climate changes on ancient wood to predict their behavior or possible failure in the future. The paper presents the initial results obtained with a new methodological approach and has a fundamental importance in the conservation of ancient wooden objects. AI algorithms have been used to clean the 3D point cloud (denoising), create voxel, hence volumetric models for FEA and for the integration of all the data for the predictive analysis. The innovative part of the project lays in (i) creation of voxel from cleaned denoised 3D point cloud; (ii) accuracy analysis of the models obtained compared with the original point cloud and the 3D mesh; (iii) direct use of these volumetric data in the FEA software for thermic analysis, using thermographic data as boundary conditions.Digital HeritageExtracting Knowledge from Digitized Asset