Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering
No full textAccurate depth estimation is at the core of many applications in computer graphics, vision, and robotics. Current state-ofthe- art monocular depth estimators, trained on extensive datasets, generalize well but lack 3D consistency needed for many applications. In this paper, we combine the strength of those generalizing monocular depth estimation techniques with multiview data by framing this as an analysis-by-synthesis optimization problem to lift and refine such relative depth maps to accurate error-free depth maps. After an initial global scale estimation through structure-from-motion point clouds, we further refine the depth map through optimization enforcing multi-view consistency via photometric and geometric losses with differentiable rendering of the meshed depth map. In a two-stage optimization, scaling is further refined first, and afterwards artifacts and errors in the depth map are corrected via nearby-view photometric supervision. Our evaluation shows that our method is able to generate detailed, high-quality, view consistent, accurate depth maps, also in challenging indoor scenarios, and outperforms state-of-the-art multi-view depth reconstruction approaches on such datasets. Project page and source code can be found at https://lorafib.github.io/ref_depth/.Vision, Modeling, and VisualizationNeural and Differentiable Renderin
Investigating Control Areas in Table Tennis
No full textControl areas are models designed to determine which portions of space can be reached by a moving entity. Such models have powerful applications in various domains where spatio-temporal information is key, ranging from urban analysis to sports spatial analysis. In this article, we explore the use of these models in table tennis to understand player strategies. We build upon existing models, originally designed for large-field or team sports, and adapt them to the adversarial context of table tennis-where the goal is to determine which regions a player can effectively return the ball to. In particular, we account for player reachability using a peripheral model that captures arm and racket positions. We report on an early evaluation of our model using TV broadcast videos and discuss potential improvements for our models.EuroVis Workshop on Visual Analytics (EuroVA)Visual Analytics Applications and System
MatSwap: Light-aware Material Transfers in Images
No full textWe present MatSwap, a method to transfer materials to designated surfaces in an image realistically. Such a task is non-trivial due to the large entanglement of material appearance, geometry, and lighting in a photograph. In the literature, material editing methods typically rely on either cumbersome text engineering or extensive manual annotations requiring artist knowledge and 3D scene properties that are impractical to obtain. In contrast, we propose to directly learn the relationship between the input material-as observed on a flat surface-and its appearance within the scene, without the need for explicit UV mapping. To achieve this, we rely on a custom light- and geometry-aware diffusion model. We fine-tune a large-scale pre-trained text-toimage model for material transfer using our synthetic dataset, preserving its strong priors to ensure effective generalization to real images. As a result, our method seamlessly integrates a desired material into the target location in the photograph while retaining the identity of the scene. MatSwap is evaluated on synthetic and real images showing that it compares favorably to recent works. Our code and data are made publicly available on https://github.com/astra-vision/MatSwapComputer Graphics ForumAppearance Modelling44
Virtual reality for chronic neck pain management: a serious game design
No full textVirtual reality has emerged as an innovative and promising therapeutic tool in the field of rehabilitation. This work presents the design and development of a tool with three interactive games, in a virtual environment, aimed at patients with chronic pain of the cervical region. Virtual environments allow the execution of therapeutic movements in a safe environment. Thereby the patients focus on the gaming experience within a controlled, motivating and recreative environment. This immersion acts as a cognitive distractor that contributes to a decrease in the fear of movement known as kinesiophobia. Preliminary results about usability suggest that this tool can be useful for rehabilitation, improving the confidence of the patients in their movement and reducing the perception of pain.Spanish Computer Graphics Conference (CEIG)Short Paper
The Hidden Legacy. Byzantine Seals of the Exarchal Age in Italian Museum Collections: a Digital Approach with SigiDoc.
No full textByzantine sigillography is an interdisciplinary field of study that examines seals once affixed to official documents within the Eastern Roman Empire and its provinces, including Italy during the so-called Exarchal period (584-751 AD). These objects offer valuable insights into various aspects of Late Antique and Medieval Mediterranean history and culture, including language (Greek and Latin), palaeography, administrative history, onomastics and prosopography, religious history, and iconography. Most scholarly editions of Byzantine seals remain in print format, often scattered into journals and miscellaneous volumes, while editions of comprehensive corpora are still limited. This project aims to conduct a systematic study and compilation of the Byzantine sigillographic heritage from the late sixth to the first half of the eighth century, focusing on material discovered in Italy or preserved in Italian museum collections. A key objective is the digitization of these objects, accompanied by the creation of metadata in accordance with the SigiDoc standard for Byzantine seals. Developed over the past decade by researchers in Paris and Cologne, SigiDoc is poised to play a crucial role in enhancing the accessibility and analysis of this rich cultural heritage. By employing SigiDoc, the project aligns with the principles of accessibility, interoperability, and reusability as defined by Digital Humanities (DH) standards. This research is supported by the CHANGES partnership, which seeks to "Cultivate Cultural Heritage Active Innovation for Next-Generation Sustainable Society.Digital HeritagePoster
Flexible, Integrable and Accessible Digital Tools for a Dynamic and Adaptive Experience of Museum Environments. The CHAMELEON project
No full textThe project CHAMELEON - Adaptable, integrable and accessible digital tools for a dynamic and adaptive use of museum environments, is focused on the Piero Leonardi Museum of Palaeontology and Prehistory, part of the Museum System of the University of Ferrara. The aim is to develo p a set of digital tools for documenting, enhancing, sharing and narrating the museum palaeontological and anthropological collections. Starting with the conceptualization of a new digital exhibition system, the accurate 3D digital acquisition of more than thirty objects have been performed. The fossils were selected considering their state of preservation, relevance and scientific representativeness, and the need to be linked to an augmented set of information. The survey, carried out through structuredlight handheld 3D scanner and digital photogrammetry, is the result of a methodological assessment highlighting the critical -interpretative and documentation opportunities that digitisation offers. The application design and development includes IT configurations aimed at managing content and virtual experiences. Responsive design, standard metadata, and open APIs support an inclusive user experience embedded in the IT architecture through applications for Semantic XR Museum, Semantic XR Avatar, 360° AR Experiences, frontside AR Experiences, and VR Experiences in specific settings. The overall outcome is a ''chameleonic'' repository able to manage on-line all the multimedia contents associated with the fruition and storytelling of tangible and intangible information.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
Bidirectional Exploration of 3D Cultural Heritage Models and Photo Collections
No full textAdvances in 3D digitization have greatly improved the availability of high-quality cultural heritage datasets, often consisting of 3D models and collections of high-resolution photos. However, navigating these 3D datasets poses challenges for art history researchers, especially when they need to repeatedly locate points of interest, get close-up views of them, and analyze their spatial relationships. Existing applications for 3D model sharing often fail to provide a convenient interface to simultaneously explore the 3D model and associated photo collections. This paper proposes a web-based approach that combines a 3D view of the model with a 2D view of a group of photos. Designers can quickly arrange groups of images into 2D projections, and cultural heritage users can explore the 3D model and, simultaneously, the active group of images in the 2D view. Both views are interlinked, so that navigating the 3D model modifies the active photo group, and clicking an image in the 2D view moves the 3D camera to the 3D position the image was taken from. We tested our approach with a 3D dataset on medieval mural paintings. Our tests show that our method helps users quickly locate, inspect and relate different parts of the model, reducing navigation time and frustration. The source code is available at https://github.com/BernatBC/visualitzador-de-fotografies-en-3D.Spanish Computer Graphics Conference (CEIG)Full Paper
Digital Technologies for Tangible and Intangible Heritage: a Preliminary Study for the Museum of Contemporary Art in San Cesario di Lecce
No full textIn the context of current debates on the digital transformation of cultural heritage institutions, this preliminary study investigates how digital technologies can support new narrative models for the valorisation of local memory within a global cultural framework. The case analysed is the Civic Museum of Contemporary Art in San Cesario di Lecce, Italy, as part of the project ''Da qui si vede tutta la città''. For this project a digital narrative path was developed to enrich visitors' engagement with both tangible and intangible dimensions of the collection, translating cultural content into a meaningful and accessible digital experience. The initiative reframes the museum as a participatory and dynamic space, where memory, creativity, and technology converge. The study outlines the conceptual framework and collaborative process underlying the intervention and anticipates a forthcoming phase of empirical evaluation through dedicated testing and user surveys.Digital HeritagePhygital Worlds and XR in Cultural Heritag
DAATSim: Depth-Aware Atmospheric Turbulence Simulation for Fast Image Rendering
No full textSimulating the effects of atmospheric turbulence for imaging systems operating over long distances is a significant challenge for optical and computer graphics models. Physically-based ray tracing over kilometers of distance is difficult due to the need to define a spatio-temporal volume of varying refractive index. Even if such a volume can be defined, Monte Carlo rendering approximations for light refraction through the environment would not yield real-time solutions needed for video game engines or online dataset augmentation for machine learning. While existing simulators based on procedurally-generated noise or textures have been proposed in these settings, these simulators often neglect the significant impact of scene depth, leading to unrealistic degradations for scenes with substantial foreground-background separation. This paper introduces a novel, physically-based atmospheric turbulence simulator that explicitly models depth-dependent effects while rendering frames at interactive/near real-time (> 10 FPS) rates for image resolutions up to 1024×1024 (real-time 35 FPS at 256×256 resolution with depth or 512×512 at 33 FPS without depth). Our hybrid approach combines spatially-varying wavefront aberrations using Zernike polynomials with pixel-wise depth modulation of both blur (via Point Spread Function interpolation) and geometric distortion or tilt. Our approach includes a novel fusion technique that integrates complementary strengths of leading monocular depth estimators to generate metrically accurate depth maps with enhanced edge fidelity. DAATSim is implemented efficiently on GPUs using Py- Torch incorporating optimizations like mixed-precision computation and caching to achieve efficient performance. We present quantitative and qualitative validation demonstrating the simulator's physical plausibility for generating turbulent video. DAATSim is made publicly available and open-source to the community: https://github.com/Riponcs/DAATSim.Computer Graphics ForumImage Creation & Augmentation44
Beyond Traditional Portals: Redirected Portals with Destination Preview for Walking in VR
No full textNatural locomotion in Virtual Reality (VR) is often constrained by the size of the physical tracking space. Portals - virtual connections between distant locations - offer a promising solution to support natural walking in limited physical areas. However, traditional portal implementations often introduce usability challenges, such as requiring large clearances from walls to prevent physical collisions, or creating unnatural transitions between spaces. In this paper, we explore four portal designs for enabling natural walking in impossible spaces: (1) Traditional Portal with a spatial preview and offset from walls; (2) Movable Portal that initially appears on a wall and can be repositioned by the user; (3) Interactive Door: a door-shaped portal embedded in the wall that can be opened interactively; (4) Revolving Door: a portal offering a continuous transition between rooms through a circular motion. These designs emerged from initial user trials that revealed the desire for more flexible and natural transitions between rooms. We conducted a user study (N=31) to evaluate these four portal types, focusing on usability, spatial understanding, immersion, and perceived naturalness. Results suggest that the alternative designs addressed the portal limitations successfully and helped convey a continuous sense of space, with each portal design revealing their strong suits. Movable Portals were commended for their sense of control, Interactive Doors for their naturalness and ease-of-use and Revolving Doors for the best feel of a continuous space, with Traditional Portals being the most preferred for their high ease-of-use.ICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual EnvironmentsEmbodiment and Navigatio