Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
An Interactive Visual Enhancement for Prompted Programmatic Weak Supervision in Text Classification
No full textProgrammatic Weak Supervision (PWS) has emerged as a powerful technique for text classification. By aggregating weak labels provided by manually written label functions, it allows training models on large-scale unlabeled data without the need for costly manual annotations. As an improvement, Prompted PWS incorporates pre-trained large language models (LLMs) as part of the label function, replacing programs coded by experts with natural language prompts. This allows for the more accessible expression of complex and ambiguous concepts. However, the existing workflow does not fully utilize the advantages of Prompted PWS, and the annotators have difficulty in effectively converging their ideas to develop high-quality LFs, and lack support during the iterations. To address this issue, this study improves the existing PWS workflow through interactive visualization. We first propose a collaborative LF development workflow between humans and LLMs, where the large language model assists humans in creating a structured development space for exploration and automatically generates prompted LFs based on human selections. Annotators can integrate their knowledge through informed selection and judgment. Then, we present an interactive visual system that supports efficient development, in-depth exploration, and iteration of LFs. Our evaluation, comprising a quantitative evaluation on the benchmark, a case study, and a user study, demonstrates the effectiveness of our approach.Computer Graphics ForumAI-Enhanced Visualizatio
Implicit Shape Avatar Generalization across Pose and Identity
No full textThe creation of realistic animated avatars has become a hot-topic in both academia and the creative industry. Recent advancements in deep learning and implicit representations have opened new research avenues, particularly in enhancing avatar details with lightweight models. This paper introduces an improvement over the state-of-the-art implicit Fast-SNARF method to permit generalization to novel motions and shape identities. Fast-SNARF trains two networks: an occupancy network to predict the shape of a character in canonical space, and a Linear Blend Skinning network to deform it into arbitrary poses. However, it requires a separated model for each subject. We extend this work by conditioning both networks on an identity parameter, enabling a single model to generalize across multiple identities, without increasing the model's size, compared to Fast-SNARF.Eurographics 2025 - Short PapersShort Paper
Differential Dynamic Gaussian Splatting: Full Scene Scalable Volumetric Video Reconstruction
No full textThe growing demand for immersive experiences in AR/VR, sports, and cinematic content is accelerating interest in volumetric video. However, existing dynamic extensions of 3D Gaussian Splatting (3DGS) methods struggle with large memory footprints, limited scalability, and impractical storage requirements-especially for long sequences on consumer-grade hardware. We present a scalable, resource-efficient pipeline for full-scene Dynamic Gaussian Splatting, achieving real-time volumetric video reconstruction on consumer-grade GPUs with <1MB per frame storage and <7.6GB memory usage, all while preserving high visual fidelity and seamless handling of emerging objects. Our method combines batch-wise differential training with per-frame PLY-based storage, enabling arbitrarily long sequences with dynamic content. By leveraging standard file formats and lightweight computation, our system lowers the barrier to entry for researchers and developers aiming to integrate high-quality volumetric video into AR/VR and interactive graphics toolchains.Computer Graphics and Visual Computing (CGVC)Computer Vision for Graphic
Exploring the Role of Visualization Tools in Enhancing Computing Education: A Systematic Literature Review
No full textVisualization aids in teaching computing by enhancing comprehension and engagement with complex concepts. This systematic literature review analyzes 90 high-quality papers selected from an initial pool of 288 to identify applications, effectiveness, and research gaps in visualization tools for computing education. We categorize tools across domains such as algorithms, programming, online learning, and problem-solving, highlighting their impact on student engagement and learning outcomes. However, we find a lack of rigorous evaluations and a need for specialized visualization models to address specific challenges. Our findings offer actionable insights for educators and researchers to improve teaching methodologies through visual strategies.EuroVis 2025 - Education PapersEducation Papers Session
Wavelet Representation and Sampling of Complex Luminaires
No full textWe contribute a technique for rendering the illumination of complex luminaires based on wavelet-compressed light fields while the direct appearance of the luminaire is handled with previous techniques. During a brief photon tracing phase, we precompute the radiance field of the luminaire. Then, we employ a compression scheme which is designed to facilitate fast per-ray run-time reconstructions of the field and importance sampling. To treat aliasing, we propose a two-component filtering solution: a 4D Gaussian filter during the pre-computation stage and a 4D stochastic Gaussian filter during rendering. We have developed an importance sampling strategy based on providing an initial guess from low-resolution and low-memory viewpoint samplers that is subsequently refined by a hierarchical process over the wavelet frequency bands. Our technique is straightforward to integrate in rendering systems and has all the features that make it practical for production renderers - MIS compatibility, brief pre-computation, low memory requirements, and efficient field evaluation and importance sampling.Computer Graphics ForumLight and Brightness44
Lipschitz Pruning: Hierarchical Simplification of Primitive-Based SDFs
No full textRendering tree-based analytical Signed Distance Fields (SDFs) through sphere tracing often requires to evaluate many primitives per tracing step, for many steps per pixel of the end image. This cost quickly becomes prohibitive as the number of primitives that constitute the SDF grows. In this paper, we alleviate this cost by computing local pruned trees that are equivalent to the full tree within their region of space while being much faster to evaluate. We introduce an efficient hierarchical tree pruning method based on the Lipschitz property of SDFs, which is compatible with hard and smooth CSG operators. We propose a GPU implementation that enables real-time sphere tracing of complex SDFs composed of thousands of primitives with dynamic animation. Our pruning technique provides significant speedups for SDF evaluation in general, which we demonstrate on sphere tracing tasks but could also lead to significant improvement for SDF discretization or polygonization.Computer Graphics ForumThe Shape of Rendering44
HERIFORGE Polish Hub As Digital Heritage Growing XR Community
No full textIn its first six months, the Polish Hub - launched under the Horizon Europe-funded HERIFORGE (cultural HERitage and Immersive technologies for innovation FORGE) project - has laid critical groundwork for fostering innovation at the intersection of cultural heritage and Extended Reality (XR) technologies. Through stakeholder mapping, policy analysis, SWOT diagnostics, and qualitative interviews, the Hub exposes structural gaps and latent potential within Poland's fragmented digital heritage landscape. It offers a participatory, place-based model that connects research, practice, and policymaking to enable long-term, cross-sectoral collaboration. As the project transitions into its 30-month implementation phase, these initial insights provide both a strategic foundation and a timely opportunity to share methodologies that can inform and inspire similar ecosystem-building efforts across Europe.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
HyperFLINT: Hypernetwork-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization
No full textWe present HyperFLINT (Hypernetwork-based FLow estimation and temporal INTerpolation), a novel deep learning-based approach for estimating flow fields, temporally interpolating scalar fields, and facilitating parameter space exploration in spatio-temporal scientific ensemble data. This work addresses the critical need to explicitly incorporate ensemble parameters into the learning process, as traditional methods often neglect these, limiting their ability to adapt to diverse simulation settings and provide meaningful insights into the data dynamics. HyperFLINT introduces a hypernetwork to account for simulation parameters, enabling it to generate accurate interpolations and flow fields for each timestep by dynamically adapting to varying conditions, thereby outperforming existing parameter-agnostic approaches. The architecture features modular neural blocks with convolutional and deconvolutional layers, supported by a hypernetwork that generates weights for the main network, allowing the model to better capture intricate simulation dynamics. A series of experiments demonstrates HyperFLINT's significantly improved performance in flow field estimation and temporal interpolation, as well as its potential in enabling parameter space exploration, offering valuable insights into complex scientific ensembles.Computer Graphics ForumFlow Vi
A Holistic Digital Ecosystem for Sustainable Cultural Heritage Management in Türkiye: National Museum Information System (MUES)
No full textThis paper presents Türkiye's National Museum Information System (MUES), a comprehensive digital platform managing 3.7 million assets in 248 public museums and 286,000 assets in 347 private museums. MUES digitizes the entire heritage lifecycle-from excavation to conservation, exhibition, and storage-standardizing workflows to boost efficiency, cut costs, enhance preservation, and combat loss and illicit trafficking. Compliant with cultural heritage laws and data governance, it offers institutional authorities granular control through a no-code, user-friendly interface, ensuring transparency and accountability. Its modular, interoperable design supports scalable adoption and integration with international heritage platforms. Beyond institutional use, MUES democratizes cultural heritage by providing real-time access to researchers, policymakers, and the public, fostering an inclusive, participatory ecosystem. Aligned with WSIS goals, MUES serves as a sustainable, replicable model for global digital heritage governance and collaboration.Digital HeritageInfrastructures, Platforms and Digital Ecosystem
FastAtlas: Real-Time Compact Atlases for Texture Space Shading
No full textTexture-space shading (TSS) methods decouple shading and rasterization, allowing shading to be performed at a different framerate and spatial resolution than rasterization. TSS has many potential applications, including streaming shading across networks, and reducing rendering cost via shading reuse across consecutive frames and/or shading at reduced resolutions relative to display resolution. Real-time TSS shading requires texture atlases small enough to be easily stored in GPU memory. Using static atlases leads to significant space wastage, motivating real-time per-frame atlassing strategies that pack only the content visible in each frame. We propose FastAtlas, a novel atlasing method that runs entirely on the GPU and is fast enough to be performed at interactive rates per-frame. Our method combines new per-frame chart computation and parametrization strategies and an efficient general chart packing algorithm. Our chartification strategy removes visible seams in output renders, and our parameterization ensures a constant texel-to-pixel ratio, avoiding undesirable undersampling artifacts. Our packing method is more general, and produces more tightly packed atlases, than previous work. Jointly, these innovations enable us to produce shading outputs of significantly higher visual quality than those produced using alternative atlasing strategies. We validate FastAtlas by shading and rendering challenging scenes using different atlasing settings, reflecting the needs of different TSS applications (temporal reuse, streaming, reduced or elevated shading rates). We extensively compare FastAtlas to prior alternatives and demonstrate that it achieves better shading quality and reduces texture stretch compared to prior approaches using the same settings.Computer Graphics ForumShady Business: Materials, Textures, and Lighting44