Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Towards interdisciplinary approaches combining AI and 2D/3D: Designing a digital environment for the virtual reconstruction of a lost medieval church using a historical ontology
No full textThis article explores the intersection of artificial intelligence (AI), 3D modeling, and historical ontology in the context of digital heritage. It presents an interdisciplinary methodology designed to enhance the accuracy and epistemological transparency of virtual reconstructions, using the lost Cordeliers Church of Nantes as a case study. Generative AI models, supported by curated databases and structured ontologies (OMeKA-S), are used to produce historically grounded visual hypotheses. The process includes source verification, bias analysis, and an iterative evaluation protocol by domain experts. The study also examines the ethical and methodological implications of using AI in the humanities, advocating for transparent, explainable, and human-centered AI workflows. By combining technical innovation with heritage expertise, this work offers a reproducible framework for digital museography and future research in the digital humanities.Digital HeritageDigitization and Segmentatio
InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions
No full textThe rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting users analytical and interaction intents. While language inputs offer flexibility, they often lack precision, making the expression of complex intents inefficient, error-prone, and time-intensive. To address these limitations, we investigate the design space of multimodal interactions for generative visual analytics through a literature review and pilot brainstorming sessions. Building on these insights, we introduce a highly extensible workflow that integrates multiple LLM agents for intent inference and visualization generation.We develop InterChat, a generative visual analytics system that combines direct manipulation of visual elements with natural language inputs. This integration enables precise intent communication and supports progressive, visually driven exploratory data analyses. By employing effective prompt engineering, and contextual interaction linking, alongside intuitive visualization and interaction designs, InterChat bridges the gap between user interactions and LLM-driven visualizations, enhancing both interpretability and usability. Extensive evaluations, including two usage scenarios, a user study, and expert feedback, demonstrate the effectiveness of InterChat. Results show significant improvements in the accuracy and efficiency of handling complex visual analytics tasks, highlighting the potential of multimodal interactions to redefine user engagement and analytical depth in generative visual analytics.Computer Graphics ForumExplainable and Generative A
Exploring and preserving Underwater Cultural Heritage through Play and Learning: the case study of CREAMARE
No full textUnderwater Cultural Heritage (UCH) plays a crucial role in understanding and preserving our shared cultural past, yet it remains one of the most overlooked and under-communicated aspects of European heritage. Compounding this issue, the oceans, which house this irreplaceable heritage, face significant environmental threats, including pollution and climate change. The CREAMARE project aims to bridge these gaps by utilizing digital technologies to raise awareness about cultural heritage (CH) and environmental preservation, while fostering collaboration between the cultural and creative sectors. Through the development of a serious game (SG), CREAMARE project offers an immersive platform that educates players on the importance of preserving both underwater cultural sites and marine ecosystems. The game provides players with the opportunity to explore 3D digital replicas of nine real UCH sites in the Mediterranean, either provided by cultural institutions or digitally reconstructed through advanced underwater technologies such as photogrammetry. The game's design incorporates a strong narrative, guiding players through a first-person adventure in which they must overcome environmental challenges and solve puzzles related to UCH preservation and ecosystem health. The development of CREAMARE's SG exemplifies a cross-sectorial, collaborative framework, bringing together project partners with creative professionals and cultural institutions selected via open calls. This participatory approach ensured that the game was not only educational but also immersive, combining historical accuracy with environmental awareness. The player's mission involves solving real-world environmental issues, such as pollution and the removal of invasive species, while simultaneously learning about the history of the submerged locations. Through this engaging experience, the game aims to inspire action and foster a deeper understanding of the critical need to protect both cultural heritage and marine ecosystems. This paper focuses on the development and testing phases of the game, highlighting the analysis of feedback from stakeholders, including players, cultural institutions, and game developers, to optimize the game's design and educational impact.Digital HeritageGame Design Methods and Application
OceanInsight: A Marine Waste Visualization Platform Empowering Community-Driven Sustainability and Coastal Cleanup Efforts
No full textThis paper explores the challenges of coastline cleaning efforts, which involve a wide range of community members, and presents a yearlong investigation into designing technology to support these cleaning tasks. It examines how participatory design research, combining interactive technology with co-design activities, can help facilitate collaboration among community-based stakeholders in alignment with the UN goals. The research delves into the difficulties stakeholders face in sharing responsibilities and collaborating effectively. This study contributes to the literature by providing new insights into designing interactive technologies that enhance stakeholder participation, foster a socially and environmentally sustainable society.EuroVis 2025 - PostersPoster
Audio-aided Character Control for Inertial Measurement Tracking
No full textPhysics-based character control generates realistic motion dynamics by leveraging kinematic priors from large-scale data within a simulation engine. The simulated motion respects physical plausibility, while dynamic cues like contacts and forces guide compelling human-scene interaction. However, leveraging audio cues, which can capture physical contacts in a costeffective way, has been less explored in animating human motions. In this work, we demonstrate that audio inputs can enhance accuracy in predicting footsteps and capturing human locomotion dynamics. Experiments validate that audio-aided control from sparse observations (e.g., an IMU sensor on a VR headset) enhances the prediction accuracy of contact dynamics and motion tracking, offering a practical auxiliary signal for robotics, gaming, and virtual environments.Eurographics 2025 - Short PapersShort Paper
Sca2Gri: Scalable Gridified Scatterplots
No full textScatterplots are widely used in exploratory data analysis. Representing data points as glyphs is often crucial for in-depth investigation, but this can lead to significant overlap and visual clutter. Recent post-processing techniques address this issue, but their computational and/or visual scalability is generally limited to thousands of points and unable to effectively deal with large datasets in the order of millions. This paper introduces Sca2Gri (Scalable Gridified Scatterplots), a grid-based post-processing method designed for analysis scenarios where the number of data points substantially exceeds the number of glyphs that can be reasonably displayed. Sca2Gri enables interactive grid generation for large datasets, offering flexible user control of glyph size, maximum displacement for point to cell mapping, and scatterplot focus area. While Sca2Gri's computational complexity scales cubically with the number of cells (which is practically bound to thousands for legible glyph sizes), its complexity is linear with respect to the number of data points, making it highly scalable beyond millions of points.Computer Graphics ForumUncertainty, Sensitivity, Scalabilit
TensoIS: A Step Towards Feed-Forward Tensorial Inverse Subsurface Scattering for Perlin Distributed Heterogeneous Media
No full textEstimating scattering parameters of heterogeneous media from images is a severely under-constrained and challenging problem. Most of the existing approaches model BSSRDF either through an analysis-by-synthesis approach, approximating complex path integrals, or using differentiable volume rendering techniques to account for heterogeneity. However, only a few studies have applied learning-based methods to estimate subsurface scattering parameters, but they assume homogeneous media. Interestingly, no specific distribution is known to us that can explicitly model the heterogeneous scattering parameters in the real world. Notably, procedural noise models such as Perlin and Fractal Perlin noise have been effective in representing intricate heterogeneities of natural, organic, and inorganic surfaces. Leveraging this, we first create HeteroSynth, a synthetic dataset comprising photorealistic images of heterogeneous media whose scattering parameters are modeled using Fractal Perlin noise. Furthermore, we propose Tensorial Inverse Scattering (TensoIS), a learning-based feed-forward framework to estimate these Perlin-distributed heterogeneous scattering parameters from sparse multi-view image observations. Instead of directly predicting the 3D scattering parameter volume, TensoIS uses learnable low-rank tensor components to represent the scattering volume. We evaluate TensoIS on unseen heterogeneous variations over shapes from the HeteroSynth test set, smoke and cloud geometries obtained from open-source realistic volumetric simulations, and some real-world samples to establish its effectiveness for inverse scattering. Overall, this study is an attempt to explore Perlin noise distribution, given the lack of any such well-defined distribution in literature, to potentially model real-world heterogeneous scattering in a feed-forward manner. Project Page: https://yashbachwana.github.io/TensoIS/Computer Graphics ForumLighting & Rendering44
Image Vectorization via Gradient Reconstruction
No full textWe present a fully automated technique that segments raster images into smooth shaded regions and reconstructs them using an optimal mix of solid fills, linear gradients, and radial gradients. Our method leverages a novel discontinuity-aware segmentation strategy and gradient reconstruction algorithm to accurately capture intricate shading details and produce compact Bézier curve representations. Extensive evaluations on both designer-created art and generative images demonstrate that our approach achieves high visual fidelity with minimal geometric complexity and fast processing times. This work offers a robust and versatile solution for converting detailed raster images into scalable vector graphics, addressing the evolving needs of modern design workflows.Computer Graphics ForumDrawn to Detail: Sketch-Based Modeling and Non-Photorealistic Rendering44
ReCoGS: Real-time ReColoring for Gaussian Splatting scenes
No full textGaussian Splatting has emerged as a leading method for novel view synthesis, offering superior training efficiency and realtime inference compared to NeRF approaches, while still delivering high-quality reconstructions. Beyond view synthesis, this 3D representation has also been explored for editing tasks. Many existing methods leverage 2D diffusion models to generate multi-view datasets for training, but they often suffer from limitations such as view inconsistencies, lack of fine-grained control, and high computational demand. In this work, we focus specifically on the editing task of recoloring. We introduce a userfriendly pipeline that enables precise selection and recoloring of regions within a pre-trained Gaussian Splatting scene. To demonstrate the real-time performance of our method, we also present an interactive tool that allows users to experiment with the pipeline in practice. Code is available at https://github.com/loryruta/recogs.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceLearning-based Algorithm
Acting Like an Expert: Analyzing Eye and Movement Behavior when Exploring Archaeological Artifacts
No full textThis study proposes a novel methodological framework for investigating the visual exploration of archaeological artifacts in both real and virtual environments, integrating eye-tracking and movement data to analyze user behavior. Focused on three vases of varying shapes and decorative registers, the research examines the influence of object characteristics and user expertise on exploration strategies. Our results reveal that while both expert and non-expert participants identify structural and diagnostic features, such as geometric patterns and manufacturing traces, experts engage in more integrative, analytical exploration, focusing on both technical and decorative aspects. In contrast, non-experts prioritize prominent visual cues, often without full comprehension of their significance. These findings demonstrate that visual behaviors are influenced both by the physical characteristics of the artifacts and by the observer's level of expertise. They also show that certain visual cues--such as shape transitions or manufacturing marks--are particularly effective in triggering recognition, even among non-experts. This study contributes to neuro-archaeology by advancing eye-tracking and users' movements analysis as tools for analyzing cognitive processes in archaeological interpretation, offering a robust, reproducible methodology that can be applied to diverse archaeological contexts, enhancing our understanding of how artifacts reveal archaeologically meaningful information through visual perception.Digital HeritageSemantics-driven Interaction with Digitized Heritag