Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
GPU Volume Rendering with Hierarchical Compression Using VDB
No full textWe propose a compression-based approach to GPU rendering of large volumetric data using OpenVDB and NanoVDB. We use OpenVDB to create a lossy, fixed-rate compressed representation of the volume on the host, and use NanoVDB to perform fast, low-overhead, and on-the-fly decompression during rendering. We show that this approach is fast, works well even in a (incoherent) Monte Carlo path tracing context, can significantly reduce the memory requirements of volume rendering, and can be used as an almost drop-in replacement into existing 3D texture-based renderers.Eurographics Symposium on Parallel Graphics and VisualizationPaper
Diminishing Returns in Perceptual Color Space - Now in Color
No full textRecent work has proven the non-Riemannian nature of perceptual color space by identifying the existence of diminishing returns along the luminance axis. A lurking question is if the luminance channel might somehow be the only axis that exhibits diminishing returns. In this short paper, we report on a companion study along two color axes: green to pink and blue to orange. These paths through color space were chosen as the most likely ones to form geodesics based on maximal agreement between color similarity experiments and hue constancy experiments. Our crowdsourced studies confirmed the existence of diminishing returns along both lines of color studied, bolstering the evidence that perceptual color space is non-Riemannian.EuroVis 2025 - Short PapersEmpirical and Perception Studie
Geometric aware local optimization for robust primitive fitting
No full textThe decomposition of 3D point clouds into meaningful geometric primitives is a longstanding challenge in Computer Vision and Computer Graphics. While recent advances in data-driven methods and neural representations have achieved significant progress in 3D reconstruction and abstraction, traditional primitive-based representations remain invaluable for tasks requiring interpretability, compactness, and robustness. This work introduces a novel framework for primitive decomposition in 2D and 3D point clouds, designed to cope with noise, outliers, and overlapping structures. Building upon traditional RANSACbased approaches, the proposed method integrates geometric priors to enhance its effectiveness in identifying interpretable and meaningful geometric primitives within complex data. Central to our approach is a novel geometric-aware inlier refinement step, which incorporates geometric constraints such as surface completeness and normal consistency. This refinement step is formulated as an optimization problem solved through the GRAPH-CUT algorithm. This optimization process penalizes excessive surface extensions and promotes coherence in normal orientations, ensuring that the refined inlier sets closely match the geometric structures the point cloud represents. Experiments on synthetic and real-world datasets validate the robustness and accuracy of the proposed method, demonstrating its ability to outperform state-of-the-art techniques in terms of both result quality and computational efficiency.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceGeometry Processin
Synchronized Multi-Frame Diffusion for Temporally Consistent Video Stylization
No full textText-guided video-to-video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text-guided image diffusion models can be extended for stylized video synthesis. However, they struggle to generate videos with both highly detailed appearance and temporal consistency. In this paper, we propose a synchronized multi-frame diffusion framework to maintain both the visual details and the temporal consistency. Frames are denoised in a synchronous fashion, and more importantly, information of different frames is shared since the beginning of the denoising process. Such information sharing ensures that a consensus, in terms of the overall structure and color distribution, among frames can be reached in the early stage of the denoising process before it is too late. The optical flow from the original video serves as the connection, and hence the venue for information sharing, among frames. We demonstrate the effectiveness of our method in generating high-quality and diverse results in extensive experiments. Our method shows superior qualitative and quantitative results compared to state-of-the-art video editing methods.Computer Graphics ForumThe Artful Edit: Stylization and Editing for Images and Video44
Procedural Multiscale Geometry Modeling using Implicit Functions
No full textMaterials exhibit geometric structures across mesoscopic to microscopic scales, influencing macroscale properties such as appearance, mechanical strength, and thermal behavior. Capturing and modeling these multiscale structures is challenging but essential for computer graphics, engineering, and materials science. We present a framework inspired by hypertexture methods, using implicit surfaces and sphere tracing to synthesize multiscale structures on the fly without precomputation. This framework models volumetric materials with particulate, fibrous, porous, and laminar structures, allowing control over size, shape, density, distribution, and orientation. We enhance structural diversity by superimposing implicit periodic functions while improving computational efficiency. The framework also supports spatially varying particulate media, particle agglomeration, and piling on convex and concave structures, such as rock formations (mesoscale), without explicit simulation. We demonstrate its potential in the appearance modeling of volumetric materials and investigate how spatially varying properties affect the perceived macroscale appearance. As a proof of concept, we show that microstructures created by our framework can be reconstructed from image and distance values defined by implicit surfaces, using both first-order and gradient-free optimization methods.Computer Graphics ForumSynthetizing 3D shapes44
Clusters in Focus: A Simple and Robust Detail-On-Demand Dashboard for Patient Data
No full textExploring tabular datasets to understand how different feature pairs partition data into meaningful cohorts is crucial in domains such as biomarker discovery, yet comparing clusters across multiple feature pair projections is challenging. We introduce Clusters in Focus, an interactive visual analytics dashboard designed to address this gap. Clusters in Focus employs a threepanel coordinated view: a Data Panel offers multiple perspectives (tabular, heatmap, condensed with histograms / SHAP values) for initial data exploration; a Selection Panel displays the 2D clustering (K-Means/DBSCAN) for a user-selected feature pair; and a novel Cluster Similarity Panel featuring two switchable views for comparing clusters. A ranked list enables the identification of top-matching feature pairs, while an interactive similarity matrix with reordering capabilities allows for the discovery of global structural patterns and groups of related features. This dual-view design supports both focused querying and broad visual exploration. A use case on a Parkinson's disease speech dataset demonstrates the tool's effectiveness in revealing relationships between different feature pairs characterizing the same patient subgroup.Eurographics Workshop on Visual Computing for Biology and MedicineSession
MVAE : Motion-conditioned Variational Auto-Encoder for tailoring character animations
No full textThe design of character animations with enough diversity is a time-consuming task in many productions such as video games or animated films, and drives the need for more simple and effective authoring systems. This paper introduces a novel approach, a motion-conditioned variational autoencoder (VAE) with Virtual reality as a motion capture device. Our model generates diverse humanoid character animations only based on a gesture captured from two Virtual reality controllers, allowing for precise control of motion characteristics such as rhythm, speed and amplitude, and providing variability through noise sampling. From a dataset comprising paired controller-character motions, we design and train our VAE to (i) identify global motion characteristics from the movement, in order to discern the type of animation desired by the user, and (ii) identify local motion characteristics including rhythm, velocity, and amplitude to adapt the animation to these characteristics. Unlike many text-tomotion approaches, our method faces the challenge of interpreting high-dimensional, non-discrete user inputs. Our model maps these inputs into the higher-dimensional space of character animation while leveraging motion characteristics (such as height, speed, walking step frequency, and amplitude) to fine-tune the generated motion. We demonstrate the relevance of the approach on a number of examples and illustrate how changes in rhythm and amplitude of the input motions are transferred to coherent changes in the animated character, while offering a diversity of results using different noise samples.ACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and EditingFrom Topology to AI: Advances in Character Animatio
An Atlas-based Approach for Appearance-aware Virtual 3D Restoration and Simulation of Fading in Fugitive Textiles
No full textSimulating the discoloration of cultural heritage garments provides valuable insights into their history and supports their preservation. For this purpose, digital methods provide innovative solutions that can leverage the realism of aging processes without causing damage to the artifact. In this work, we propose a method to render color changes in two fugitive textiles housed at the Victoria and Albert Museum. We use a combination of novel atlas-based material segmentation and color restoration approaches to transfer appearance from textile mockups to the 3D models of the garments. The fading effects are induced with accelerated aging on mockups that are chemical proxies of the historic garments, with their aging monitored colorimetrically and spectrally, and their appearance measured with a total appearance capture device. Our proposed approach generates a colour-cue-based segmentation map over a 3D surface, followed by appearance transfer to segmented regions from mockups and fading simulations from spectral unmixing, along with appearance-aware restoration optimized using a reference image. By facilitating appearance-aware fading simulation in virtual 3D models in an interactive app, our approach supports a realistic visualization of colour change in the past and the future. We evaluate our method on two heritage garments - a 20th-century kimono and a 19th-century Victorian dress featuring different fabrics (silk and cotton) and dyed with natural and synthetic materials. In accordance with data collected through scientific analysis measurements, the proposed method effectively transfers a visual appearance that is both plausible and consistent with the data, providing both specialists and lay audiences with a range of fading simulations to support interpretation and restoration decisions.Digital HeritagePERCEIVE: Exhibiting the ''Unexhibitable'
Uncertainty-Aware Visualization of Biomolecular Structures
No full textMolecular structure visualization is fundamental to molecular biology, aiding in understanding complex biological processes. While advancements in molecular visualization have greatly improved the representation of these structures, inherent uncertainties-such as inaccuracies in atomic positions or variability in secondary structure classifications-impact the accuracy of the visualizations. Uncertainty-aware visualization (UAV) emerged as a response to these challenges, integrating uncertainty into visual representations to improve data interpretation and decisionmaking. Despite extensive work on both molecular and uncertainty visualization (UV), there is a lack of comprehensive surveys addressing the intersection of these two fields. This paper provides a state-of-the-art review of UAV approaches for biomolecular structures. We propose a classification schema that organizes existing methods based on the type of molecule visualized, the manifestation of uncertainty, and the mapping of uncertainty to a visual representation. Using this framework, we identified research gaps and areas for future exploration in uncertainty-aware biomolecular structure visualization.Computer Graphics ForumDomain-Specific Visualization Application
Rose Charts: Area or Length Encoding for Fill Level of Circle Sectors?
No full textThis paper examines the accuracy of value estimation from the fill level in circle sectors of rose charts, a circular chart type where all sectors share the same angle and encode values through either radius or area. But which encoding yields more accurate estimates? We conducted a user study comparing different sector configurations and chart sizes as well as the estimation errors of rose versus bar charts. Our findings indicate that both area and radius influence estimation accuracy. For values below 65%, area dominates as a visual cue, whereas for larger values, a transition to length perception can be observed. Based on these insights, we propose a transfer function to correct for average estimation errors and provide practical guidelines for the effective use of rose charts.EuroVis 2025 - Short PapersEmpirical and Perception Studie