Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Expressive Rendering for 2D Animations of Liquids
No full textWe describe a new rendering technique for expressive liquid surface 2D animation that can be used on top of existing particlebased simulations. We introduce a hybrid particle model that carries both water and air density distribution and can evolve through particle history. These material quantities combined with the kinematics information are then used to generate a scalar field, which can be parameterized to create an implicit iso-surface capturing stylized geometry commonly seen in paintings and cartoons. We propose, in particular, to represent behavior highlighting the dynamical aspect of the scene, such as elongated droplet behavior and curl-like shapes found in breaking waves.ACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and Editing - Artworks, Posters, DemosPoster
C2Views: Knowledge-based Colormap Design for Multiple-View Consistency
No full textMultiple-view (MV) visualization provides a comprehensive and integrated perspective on complex data, establishing itself as an effective method for visual communication and exploratory data analysis. While existing studies have predominantly focused on designing explicit visual linkages and coordinated interactions to facilitate the exploration of MV visualizations, these approaches often demand extra graphical and interactive effort, overlooking the potential of color as an effective channel for encoding data and relationships. Addressing this oversight, we introduce C2Views, a new framework for colormap design that implicitly shows the relation across views. We begin by structuring the components and their relationships within MVs into a knowledge-based graph specification, wherein colormaps, data, and views are denoted as entities, and the interactions among them are illustrated as relations. Building on this representation, we formulate the design criteria as an optimization problem and employ a genetic algorithm enhanced by Pareto optimality, generating colormaps that balance single-view effectiveness and multiple-view consistency. Our approach is further complemented with an interactive interface for user-intended refinement. We demonstrate the feasibility of C2Views through various colormap design examples for MVs, underscoring its adaptability to diverse data relationships and view layouts. Comparative user studies indicate that our method outperforms the existing approach in facilitating color distinction and enhancing multiple-view consistency, thereby simplifying data exploration processes.Pacific Graphics Conference Papers, Posters, and DemosVisualizatio
Cutting Through the Clutter: The Potential of LLMs for Efficient Filtration in Systematic Literature Reviews
No full textSystematic literature reviews (SLRs) are essential but labor-intensive due to high publication volumes and inefficient keywordbased filtering. To streamline this process, we evaluate Large Language Models (LLMs) for enhancing efficiency and accuracy in corpus filtration while minimizing manual effort. Our open-source tool LLMSurver presents a visual interface to utilize LLMs for literature filtration, evaluate the results, and refine queries in an interactive way. We assess the real-world performance of our approach in filtering over 8.3k articles during a recent survey construction, comparing results with human efforts. The findings show that recent LLM models can reduce filtering time from weeks to minutes. A consensus scheme ensures recall rates >98.8%, surpassing typical human error thresholds and improving selection accuracy. This work advances literature review methodologies and highlights the potential of responsible human-AI collaboration in academic research.EuroVis Workshop on Visual Analytics (EuroVA)Visual Analytics Applications and System
MF-SDF: Neural Implicit Surface Reconstruction using Mixed Incident Illumination and Fourier Feature Optimization
No full textThe utilization of neural implicit surface as a geometry representation has proven to be an effective multi-view surface reconstruction method. Despite the promising results achieved, reconstructing geometry from objects in real-world scenes remains challenging due to the interaction between surface materials and complex ambient light, as well as shadow effects caused by self-occlusion, making it a highly ill-posed problem. To address this challenge, we propose MF-SDF, a method that use a hybrid neural network and spherical gaussian representation to model environmental lighting, so that the model can express the situation of multiple light sources including directional light (such as outdoor sunlight) in real-world scenarios. Benefit from this, our method effectively reconstructs coherent surfaces and accurately locates the shadow location on the surface. Furthermore, we adopt a shadow aware multi-view photometric consistency loss, which mitigates the erroneous reconstruction results of previous methods on surfaces containing shadows, thereby improve the overall smoothness of the surface. Additionally, unlike previous approaches that directly optimize spatial features, we propose a Fourier feature optimization method that directly optimizes the tensorial feature in the frequency domain. By optimizing the high-frequency components, this approach further enhances the details of surface reconstruction. Finally, through experiments, we demonstrate that our method outperforms existing methods in terms of reconstruction accuracy on real captured data.Computer Graphics ForumSynthetizing 3D shapes44
HeriTwinneD: Digital Twin Application in Heritage Buildings Within the Smart City Bamberg
No full textAdvancements in intelligent systems and the widespread application of sensor-based technologies have introduced innovative approaches to the conservation of architectural heritage. Among them, the concept of the Digital Twin, a dynamic, data-integrated digital replica of a physical asset, has emerged as a promising solution for documentation, performance optimization, and predictive maintenance within the context of heritage buildings. Although the Digital Twin was initially developed in the manufacturing and aerospace sectors, this concept has gradually expanded into the built environment, and the application of this technology is now being explored in cultural heritage that aspires to align technological innovation with conservation imperatives. This project, HeriTwinneD, is a PhD project being carried out at the Chair of Digital Technologies in Heritage Conservation at the University of Bamberg, and is also part of the Smart City graduate school in Bamberg (BaGSCiS). It explores the potential of Digital Twin in architectural heritage in Bamberg, a UNESCO World Heritage Site since 1993 and a Smart City since 2020 in Germany. Through the integration of real-time sensor data, 3D modeling techniques, and interdisciplinary collaboration, this study aims to demonstrate how Digital Twin can contribute to sustainable, informed, and inclusive strategies for the conservation of heritage buildings in the digital age.Digital HeritagePoster
ReConForM: Real-time Contact-aware Motion Retargeting for more Diverse Character Morphologies
No full textPreserving semantics, in particular in terms of contacts, is a key challenge when retargeting motion between characters of different morphologies. Our solution relies on a low-dimensional embedding of the character's mesh, based on rigged key vertices that are automatically transferred from the source to the target. Motion descriptors are extracted from the trajectories of these key vertices, providing an embedding that contains combined semantic information about both shape and pose. A novel, adaptive algorithm is then used to automatically select and weight the most relevant features over time, enabling us to efficiently optimize the target motion until it conforms to these constraints, so as to preserve the semantics of the source motion. Our solution allows extensions to several novel use-cases where morphology and mesh contacts were previously overlooked, such as multi-character retargeting and motion transfer on uneven terrains. As our results show, our method is able to achieve real-time retargeting onto a wide variety of characters. Extensive experiments and comparison with state-of-the-art methods using several relevant metrics demonstrate improved results, both in terms of motion smoothness and contact accuracy.Computer Graphics ForumRigged for Success: Character Animation and Retargeting44
C3DHN - An evolutive French Ecosystem for heritage data preservation: methodology, technologies and community
No full textThe preservation of 3D heritage data is a major challenge for scientific research and the enhancement of cultural heritage. This article presents the structured approach developed by the French community for conserving and utilizing these data, federated within a dedicated national infrastructure: the Consortium 3D for Digital Humanities (CST3D HN). Activities are organized around four main axes: a shared and common methodology, the use of standardized metadata and an open source software tool named Altag3D, the development of the French National 3D Data Repository Archive, and the structuring of a dedicated French scientific community in the form of a scholarly society. https://3dhumanities.hypotheses.org The CST3D HN methodology relies on proven principles for documenting and structuring 3D heritage data. It establishes standards to ensure FAIR principles, particularly interoperability, sustainability, and data accessibility. This methodological framework ensures rigorous project management and harmonization of practices among various involved institutions, extending beyond disciplinary specifics. Multimodal digitization has become essential in the heritage domain. However, point clouds and models can only make sense if associated descriptors are provided. Metadata management is an essential step to ensure data traceability and reuse. The open-source software Altag3D was developed by the entire community: it is based on a structured and interoperable metadata model. Our schema, initially limited to the fields of archaeology and cultural heritage, is now open to other areas of the human sciences. It is aligned with standard vocabularies and mapped to the Europeana Data Model (EDM). Altag3D allows to annotate, to document and to archive 3D models with respect to FAIR principles (Findable, Accessible, Interoperable, Reusable) thus aiming for standardization of 3D heritage data. https://altag3d.huma-num.fr The third axis involves setting up the French National Conservatoire for 3D heritage data, which aims to centralize and preserve French 3D heritage productions. This Open Archival Information System (OAIS) infrastructure for research data in France is hosted by the CINES (Centre Informatique National de l'Enseignement Supérieur). Thanks to Altag3D which helps researchers to create their own OAIS Submission Information Package (SIP), 3D models can be stored for next generations; a guarantee of interoperability for at least 20 to 30 years is ensured. The Data Repository assigns a Digital Object Identifier to each submission and introduces numerous innovations, such as using the GLTF format for improved visualization of models. This initiative is part of a long-term conservation and open data strategy, promoting their exploitation by researchers, institutions, and the general public. https://3d.humanities.science These technological and methodological advancements would not be sufficient without the creation of a national scientific community dedicated to heritage 3D at the French scale. The Consortium brings together over 44 members, including academic, institutional, and industrial actors, promoting interdisciplinary exchanges and dissemination of best practices. Within this dynamic, creating a scholarly society aims to ensure the sustainability of this community, structuring its activities (workshops, scientific events, publications), and enhancing its integration within national and international networks.Digital HeritageInfrastructures, Platforms and Digital Ecosystem
Fine-Tuning LayoutParser for the Analysis of Historical Italian Newspapers
No full textWe present an initiative aimed at fine-tuning the LayoutParser framework to develop an AI model capable of understanding and decomposing newspaper pages. If successful, this effort would enable the large-scale processing of entire years of Italian newspaper issues, offering significant benefits to a wide range of researchers across multiple disciplines.Digital HeritagePoster
Attention-Guided Multi-scale Neural Dual Contouring
No full textReconstructing high-quality meshes from binary voxel data is a fundamental task in computer graphics. However, existing methods struggle with low information density and strong discreteness, making it difficult to capture complex geometry and long-range boundary features, often leading to jagged surfaces and loss of sharp details.We propose an Attention-Guided Multiscale Neural Dual Contouring (AGNDC) method to address this challenge. AGNDC refines surface reconstruction through a multi-scale framework, using a hybrid feature extractor that combines global attention and dynamic snake convolution to enhance perception of long-range and high-curvature features. A dynamic feature fusion module aligns multi-scale predictions to improve local detail continuity, while a geometric postprocessing module further refines mesh boundaries and suppresses artifacts. Experiments on the ABC dataset demonstrate the superior performance of AGNDC in both visual and quantitative metrics. It achieves a Chamfer Distance (CD×105) of 9.013 and an F-score of 0.440, significantly reducing jaggedness and improving surface smoothness.Pacific Graphics Conference Papers, Posters, and Demos3D Reconstructio
Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?
No full textSince its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray-marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in-depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.Computer Graphics ForumSplat-tacular Radiance Fields44