Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Eurographics Workshop on Visual Computing for Biology and Medicine: Short Papers Frontmatter
No full textEurographics Workshop on Visual Computing for Biology and Medicin
A Region-Based Facial Motion Analysis and Retargeting Model for 3D Characters
No full textWith the expanding applicable scenarios of 3D facial animation, abundant research has been done on facial motion capture, 3D face parameterization, and retargeting. However, current retargeting methods still struggle to reflect the source motion on a target 3D face accurately. One major reason is that the source motion is not translated into precise representations of the motion meanings and intensities, resulting in the target 3D face presenting inaccurate motion semantics. We propose a region-based facial motion analysis and retargeting model that focuses on predicting detailed facial motion representations and providing a plausible retargeting result through 3D facial landmark input. We have defined the regions based on facial muscle behaviours and trained a motion-to-representation regression for each region. A refinement process, designed using an autoencoder and a motion predictor for facial landmarks, which works for both real-life subjects' and fictional characters' face rigs, is also introduced to improve the precision of the retargeting. The region-based strategy effectively balances the motion scales of the different facial regions, providing reliable representation prediction and retargeting results. The representation prediction and refinement with 3D facial landmark input have enabled flexible application scenarios such as video-based and marker-based motion retargeting, and the reuse of animation assets for Computer-Generated (CG) characters. Our evaluation shows that the proposed model provides semantically more accurate and visually more natural results than similar methods and the commercial solution from Faceware. Our ablation study demonstrates the positive effects of the region-based strategy and the refinement process.Pacific Graphics Conference Papers, Posters, and DemosCharacter Animatio
Personalized Visual Dubbing through Virtual Dubber and Full Head Reenactment
No full textVisual dubbing aims to modify facial expressions to ''lip-sync'' a new audio track. While person-generic talking head generation methods achieve expressive lip synchronization across arbitrary identities, they usually lack person-specific details and fail to generate high-quality results. Conversely, person-specific methods require extensive training. Our method combines the strengths of both methods by incorporating a virtual dubber, a person-generic talking head, as an intermediate representation. We then employ an autoencoder-based person-specific identity swapping network to transfer the actor identity, enabling fullhead reenactment that includes hair, face, ears, and neck. This eliminates artifacts while ensuring temporal consistency. Our quantitative and qualitative evaluation demonstrate that our method achieves a superior balance between lip-sync accuracy and realistic facial reenactment.Eurographics 2025 - Short PapersShort Paper
Run-time Performance Comparison of Sparse-set and Archetype Entity-Component Systems
No full textEntity-Component System (ECS) architectures have emerged as a powerful alternative to traditional object-oriented solutions in video games and real-time simulations. However, different ECS implementations present distinct trade-offs between iteration speed and modification costs. Despite its growing adoption, a comparative analysis on the performance characteristics of ECS implementation types has yet to be conducted. This study compares the performance of two widely-used ECS implementations: sparse-set and archetype-based. To facilitate this, an implementation of each architecture was developed in C++20 and their performance was examined in terms of iteration speed and entity modification costs. The results show sparse-set ECSes enable cheaper entity modifications but scale poorly during iteration, while archetypes excel at large-scale iteration through cache efficiency but incur higher composition change costs. These findings provide valuable and actionable guidance for developers selecting ECS architectures for their specific applications.Computer Graphics and Visual Computing (CGVC)Game
Four years of sharing teaching practices within the French Computer Graphics community
No full textThis paper describes and provides feedback on a Computer Graphics (CG) teaching initiative conducted by the French Association of CG (AFIG in French), as part of its annual national conference (called j.FIG). The AFIG, historically focused primarily on research and doctoral education, has been leading the French academic community in CG for 30 years. Since the beginning of 2021, it has launched a working group dedicated to CG teaching in the Bachelor's and Master's cycles. Its main action was to present panels during the j.FIG, to address issues related to CG teaching on a national scale. This is analyzed in detail in this paper. For each of the four organized panels so far, we present its main goals and the underlying discussions and repercussions, by comparing them with similar state-of-the-art initiatives. Possible actions and proposals to perpetuate the event are finally discussed. More broadly, our ambition is to obtain reactions and provoke necessarily enriching discussions, enabling everyone to escape a little from the teacher's solitude, alone in front of his class.Eurographics 2025 - Education PapersEducation
Self-Supervised Neural Global Illumination for Stereo-Rendering
No full textWe propose a novel neural global illumination baking method for real-time stereoscopic rendering, with applications to virtual reality. Naively, applying neural global illumination to stereoscopic rendering requires running the model per eye, which doubles the computational cost making it infeasible for real-time virtual reality applications. Training a stereoscopic model from scratch is also impractical, as it will require additional path tracing ground truth for both eyes. We overcome these limitations by first training a common neural global illumination baking model using a single eye dataset. We then use self-supervised learning to train a second stereoscopic model using the first model as a teacher model, where we also transfer the weights of the first model to the second model to accelerate the training process. Furthermore, our spatial coherence loss encourages consistency between the rendering for two eyes. Experiments show our method achieves the same quality as the original single-eye model with minimal overhead, enabling real-time performance in virtual reality.Pacific Graphics Conference Papers, Posters, and DemosPosters and Demo
Mapping Pausania: A GIS-Based Reconstruction of the Laconian Landscape
No full textThe archaeological landscape of ancient Greece is a paradigmatic case study for cultural heritage research, not only because of the sheer amount of identified remains, but also because of the many ancient texts referring to such elements. In this regard, among the surviving literary works from antiquity, the Periegesis of Pausanias represents a valuable asset, whose exhaustiveness in firsthand descriptions has exerted a strong influence on modern research. The narrative of the text, structured as a series of itineraries, is particularly suitable for the creation of digital maps which may recreate ancient landscapes and compare them with the current state of research. In particular, the region of Laconia has proven to be promising in light of the state of partial decay already observed in Roman times, by the time of the author's analysis. Therefore, the area has been isolated as a case study and recreated in the form of three GIS maps by using the ArcGIS software, focusing respectively on Laconia in the classical age, in the Roman age, and in the current state. As such, the three maps may be used simultaneously for synchronic and diachronic investigations of the region, thereby enabling the evaluation of the peculiarities of the studied landscape and heritage. The data visualized in the digital maps is derived from a critical analysis of the text and associated with comments based on the state of the art, which not only enhance the study of the mapped remains but also allow for the assessment of the state of identification of the landscape treated by Pausanias. The georeferenced database, built to support the spatial analysis and the data visualization, aims to overcome the limitations generally inherent to other thesauri and gazetteers of the classical world, thanks to a taxonomy that allows for the rapid isolation of salient features of the mapped data. Data such as the time period, the actual state of identification, modern toponymy, and the typology of the remains can be quickly researched, thus enabling several kinds of queries. All the produced cartography is also intended to be uploaded online by using the ArcGIS Online cloud platform, with the aim to create a web application that ensures maximum visibility and easy access to the mapped material.Digital HeritageAnalysing and Documenting Sites and Landscape
From Optical Measurement to Visual Comfort Analysis: a Complete Simulation Workflow with Ocean™'s Glare Map Post-processing
No full textLighting critically influences public safety and visual comfort across environments. Discomfort glare, in particular, poses a major challenge. We here introduce Ocean™'s glare map, a fast, high-fidelity glare evaluation tool that computes key indices (UGR, DGP, GR) through post-processing of spectral global illumination simulations. Beyond whole-scene assessments, our glare map tool uniquely offers per-source glare ratings, enabling precise design optimization. Through three practical use cases, we demonstrate the effectiveness of our tool for operational design and show how changes in illumination and material properties directly affect glare, supporting safer and more efficient lighting designs.Eurographics Symposium on RenderingLight and Brightnes
VRSurf: Surface Creation from Sparse, Unoriented 3D Strokes
No full textAlthough intuitive, sketching a closed 3D shape directly in an immersive environment results in an unordered set of arbitrary strokes, which can be difficult to assemble into a closed surface. We tackle this challenge by introducing VRSurf, a surfacing method inspired by a balloon inflation metaphor: Seeded in the sparse scaffold formed by the strokes, a smooth, closed surface is inflated to progressively interpolate the input strokes, sampled into lists of points. These are treated in a divide-and-conquer manner, which allows for automatically triggering some additional balloon inflation followed by fusion if the current inflation stops due to a detected concavity. While the input strokes are intended to belong to the same smooth 3D shape, our method is robust to coarse VR input and does not require strokes to be aligned. We simply avoid intersecting strokes that might give an inconsistent surface position due to the roughness of the VR drawing. Moreover, no additional topological information is required, and all the user needs to do is specify the initial seeding location for the first balloon. The results show that VRsurf can efficiently generate smooth surfaces that interpolate sparse sets of unoriented strokes. Validation includes a side-by-side comparison with other reconstruction methods on the same input VR sketch. We also check that our solution matches the user's intent by applying it to strokes that were sketched on an existing 3D shape and comparing what we get to the original one.Computer Graphics ForumDrawn to Detail: Sketch-Based Modeling and Non-Photorealistic Rendering44
Enduring Memory: Participatory Digital Experiences for Exploring the Contemporary Past at Camp 65
No full textThe educational project ''La memoria che resta'' (''The Memory That Remains'') aimed to raise awareness of contemporary historical-archaeological heritage through a collaboration between archaeologists from the University of Bari ''Aldo Moro'' and students from the ''Cagnazzi'' High School in Altamura. Focused on Camp 65, one of Italy's largest prisoner-of-war camps, the project combined mobile mapping and 3D surveying using accessible digital tools such as QField and iPhones equipped with integrated LiDAR. During the dissemination phase, students were actively involved in the documentation process and later developed digital storytelling content to reflect on and communicate their field experiences. This participatory approach effectively fostered interdisciplinary skills and a deeper understanding of the site's historical significance within the local community.Digital HeritageFrom DH Theory and Principles to Innovative Practice: Participation, Training, and Acces