Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Learning Image Fractals Using Chaotic Differentiable Point Splatting
No full textFractal geometry, defined by self-similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient-based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high-quality fractal codes and perform extensive zoom-ins to reveal intricate patterns from just a single image.Computer Graphics ForumEclipsing the Ordinary in Visualization44
Investigation into Virtual Reality Movement Methods
No full textThis paper critically examines different methods for traversing virtual reality (VR) environments, providing an analysis of their effectiveness. The primary objective is to outline and assess various locomotion techniques, including, but not limited to, teleportation and joystick-based movement. Each method is evaluated based on key performance indicators: its believability, which measures how well the movement aligns with a user's natural expectations of motion; its smoothness, which speaks to the fluidity and consistency of the movement; and its potential to induce motion sickness, a critical factor for long-term playability and user comfort. Through this detailed comparative analysis, the paper aims to draw a well-supported conclusion regarding the optimal VR locomotion method, identifying which traversal technique offers the most balanced and effective solution for developers and users.Computer Graphics and Visual Computing (CGVC)Short Papers Session: Games and Graphic
Perspective Crop Based Egocentric Hand Pose Estimation via Fisheye Stereo Vision
No full textIn this paper, we propose a method to improve the performance of hand pose estimation from egocentric view. To accurately capture hands moving within a wide range in daily activities, we mounted a fisheye stereo camera on a head mounted display to obtain wide-angle images from egocentric view. Our proposed two-stage method addresses the camera distortion introduced by this setup. The 2D hand keypoints estimated by stage-1 HandNet are converted into 3D hand keypoints through triangulation for perspective cropping. Stage-2 HandNet then predicts the final 2D hand keypoints from the undistorted hand crop image. To train stage-1 HandNet for perspective cropping, we built FisheyeEgoHAND dataset which consists of three categories of scenarios (separate hand, hand-hand, and hand-object) that reflect various hand interactions in an egocentric view. Through experiments, we demonstrated that two-stage 2D hand pose estimation outperforms one-stage approach without perspective cropping.Eurographics 2025 - PostersPoster
Iterative Nonparametric Bayesian CP Decomposition for Hyperspectral Image Denoising
No full textHyperspectral image (HSI) denoising relies on exploiting the multiway correlations hidden in the clean signals to discriminate between the randomness of measurement noise. This paper proposes a self-supervised model that has a three-layer algorithmic hierarchy to iteratively quest for the tensor decomposition based representation of the underlying HSI. The outer layer takes advantage of the non-local similarity of HSI via a simple but effective k-means++ algorithm to explore the patch-level correlation and yields clusters of patches with similar tensor ranks. The middle and inner layers consist of a Bayesian Nonparametric tensor decomposition framework. The middle one employs a multiplicative Gamma process prior for the low rank tensor decomposition, and a Gaussian-Wishart prior for a more flexible exploration of the correlations among the latent factor matrices. The inner layer is responsible for the finer regression of the residual multiway correlations leaked from the upper two layers. Our scheme also provides a principled and automatic solution to several practical HSI denoising factors, such as the noise level, the model complexity and the regularization weights. Extensive experiments validate that our method outperforms state-of-the-art methods on a series of HSI denoising metrics.Eurographics Symposium on RenderingStylization and Image Processin
Designing UI for a VR Environment: Diegetic and Non-diegetic Approaches
No full textThe integration of effective user interfaces (UI) is critical in the rapidly evolving landscape of video games and particularly within virtual reality (VR). Poor UI design can have a negative impact on immersion by breaking such engagement, create cognitive overload, and detract from the overall experience of the player. This paper investigates a strategic implementation of two primary categories: diegetic interfaces, which are integrated into the game world, and non-diegetic interfaces, which exist outside the games fictional space. A simple VR game was created to test both diegetic and non-diegetic UI principles gaining feedback to assess the purpose and usability of the two methods for the application into future projects and research.Computer Graphics and Visual Computing (CGVC)Short Papers Session: VR and M
Fairness-Aware Urban Planning in Sweden: An Interactive Visualization Tool for Equitable Cities
No full textThis study presents an interactive visualization tool that facilitates fairness-aware urban planning. The system introduces a fairness scale to assess the accessibility of potential new developments, using color-coded scatter plots to visualize disparities. An intuitive interaction design minimizes complexity while enhancing usability, enabling users to analyze urban infrastructure and services. Developed with web technologies, the tool leverages OpenStreetMap data to ensure adaptability across different cities. Future optimizations include advanced analytical capabilities and broader dataset integrations to improve decisionmaking in urban development.EuroVis 2025 - PostersPosters and Demo
Lessons from the Pumpkin Patch: Building Community and Visualization Literacy with Physical Visualization
No full textTeaching introductory visualization classes is a challenging job. These courses often attract students with wide range of prior preparation, and many arrive without formal training in the foundations of computing or statistics. Further, educators face the challenge of growing and adapting in response to new best practices for inclusive and accessible computational education. In this paper, we present a case study documenting a class-wide physical visualization project designed to foster a classroom learning community, reinforce the principle of data-visual mapping, and engage students in a creative and community-focused data project. Guided by inclusive pedagogy and learning science principles of scaffolding, constructivism, and constructionism, the project challenged students to create a physical visualization out of carved pumpkins that would engage the campus community. Student responses to the project were overall extremely positive. An evaluation of the project showed students walked away with increased respect for large-scale projects, a deeper understanding of data-visual mapping, pride and awe in their creation, an increased sense of classroom and campus community, and appreciation for the accessibility of the project.EuroVis 2025 - Education PapersEducation Papers Session
Designing a Virtual Museum Ecosystem for the Cloud
No full textDigital exhibits are often commissioned from specialist organisations for a premium price and only available to prestigious national and international organisations that have the budget to match. Yet developments in underlying technologies, such as commodity computers, mobiles and networks, are increasingly capable of delivering rich heritage experiences. Consequently, the possibility of immersive and mobile technologies becoming part of the normal offering of community museums is in reach. A virtual museum ecosystem, which empowers community-based museums to embrace technologies to digitally enhance the capacities of a museum supporting the research, collection, curation and communication of heritage, has the potential both to contribute to sustainable development as well as mitigate against the threats to heritage.Digital HeritageCollaborative Cloud for CH (ECHOES SESSION
Heritage Within the Community's Reach Through the Use of New Technologies: The Vila Verde House of Knowledge
No full textThis research project explores the application of new technologies to the preservation, communication, and enhancement of cultural heritage in Vila Verde, Portugal. By focusing on both tangible and intangible heritage-ranging from archaeological sites and historic architecture to festivals, crafts, and oral traditions-the project aims to foster community engagement and contribute to the consolidation of national memory. Leveraging the House of Knowledge as a local innovation hub, the study employs an action research methodology structured around four phases: identifying heritage assets and best practices; creating digital archives and interactive platforms using tools such as ArcGIS Experience Builder; disseminating knowledge through multimedia exhibitions and community participation; and evaluating the impact on cultural identity and local tourism. The inventory includes over 80 cultural spaces and audiovisual recordings from key museums, ensuring a comprehensive and participatory approach. This project demonstrates how digital culture and repositories can revitalise rural heritage and promote inclusive, sustainable heritage management.Digital HeritagePoster
Perceptive Enhanced Realities of Coloured Collections through AI and Virtual Experiences
No full textPERCEIVE (Perceptive Enhanced Realities of Coloured Collections through AI and Virtual Experiences) is an European project dedicated to the study, analysis, interpretation, reconstruction, conservation and communication of colours in artwork and historical objects, within five different scenarios, including: lost polychromy of ancient sculptures, fading colours of paintings and works on arts, of textiles, of historical photo and film collections and colour of digital born art. This paper describes the methodology and presents the main results beyond the state of the art.Digital HeritagePERCEIVE: Exhibiting the ''Unexhibitable'