Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
A Proposal for Proactive Quality Assurance in Photogrammetry Workflows: Using Smart-device LiDAR for Scaling
No full textThis preliminary project report proposes a low-cost quality assurance step for digital documentation workflows using consumer-grade LiDAR on mobile smart devices. We explore if LiDAR-generated meshes can be used to scale photogrammetry models post hoc, addressing scaling errors caused by human input. Preliminary tests on replica cultural heritage objects show scaling accuracy within 3.5% of photogrammetric reference models, with minimal local deviation. The method is fast, relatively low-cost, and requires almost no specialized training, making it a practical fallback in constrained field conditions. While not a replacement for traditional methods, it has the capacity to improve the reliability of digitization workflows with minimal overhead.Digital HeritagePoster
Volume Preserving Neural Shape Morphing
No full textShape interpolation is a long standing challenge of geometry processing. As it is ill-posed, shape interpolation methods always work under some hypothesis such as semantic part matching or least displacement. Among such constraints, volume preservation is one of the traditional animation principles. In this paper we propose a method to interpolate between shapes in arbitrary poses favoring volume and topology preservation. To do so, we rely on a level set representation of the shape and its advection by a velocity field through the level set equation, both shape representation and velocity fields being parameterized as neural networks. While divergence free velocity fields ensure volume and topology preservation, they are incompatible with the Eikonal constraint of signed distance functions. This leads us to introduce the notion of adaptive divergence velocity field, a construction compatible with the Eikonal equation with theoretical guarantee on the shape volume preservation. In the non constant volume setting, our method is still helpful to provide a natural morphing, by combining it with a parameterization of the volume change over time. We show experimentally that our method exhibits better volume preservation than other recent approaches, limits topological changes and preserves the structures of shapes better without landmark correspondences.Computer Graphics ForumAnimation and Morphing44
NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
No full textIn this paper, we introduce NoPe-NeRF++, a novel local-to-global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods, particularly NoPe-NeRF, which focus solely on the local relationships within images, often struggle to recover accurate camera poses in complex scenarios. To overcome the challenges, our approach begins with a relative pose initialization with explicit feature matching, followed by a local joint optimization to enhance the pose estimation for training a more robust NeRF representation. This method significantly improves the quality of initial poses. Additionally, we introduce global optimization phase that incorporates geometric consistency constraints through bundle adjustment, which integrates feature trajectories to further refine poses and collectively boost the quality of NeRF. Notably, our method is the first work that seamlessly combines the local and global cues with NeRF, and outperforms state-of-the-art methods in both pose estimation accuracy and novel view synthesis. Extensive evaluations on benchmark datasets demonstrate our superior performance and robustness, even in challenging scenes, thus validating our design choices.Computer Graphics ForumSplat-tacular Radiance Fields44
Influence of Non-Isomorphic Interactions on Users' Agency with a Dissimilar Avatar in Virtual Reality
No full textThe user's perception in Virtual Reality (VR) with avatars is strongly influenced by the Sense of Embodiment (SoE) and Sense of Agency (SoA). However, traditional VR interfaces often rely on human-centric interactions (e.g., hand or raycast) that may not translate well to dissimilar avatars that differ from human anatomy. This paper describes the design and evaluation of selection and navigation metaphors in VR for a dissimilar avatar. We introduce StretchIK, an adaptation of the Forward Backward Reaching Inverse Kinematics that works with non-isomorphic interaction metaphors. We conducted two user studies to investigate the influence of the interaction metaphors on users' SoE and SoA. In the first study, we compared two selection metaphors (Go-go versus Head-Selection), where participants had to grab virtual cabbages. In the second study, we compared two navigation metaphors (3D steering versus 3D Leaning), where participants had to travel through virtual rings. The results showed that users had a good SoE in the dissimilar avatar for interacting. However, the interaction metaphors affected users' performance, SoA, where Go-Go outperformed Head-Selection, and 3D steering outperformed 3D Leaning. Our results could improve interaction with dissimilar avatars, eliciting potential future work regarding shared control of dissimilar avatars in VR.ICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual EnvironmentsEmbodiment and Navigatio
Self-Supervised Image Harmonization via Region-Aware Harmony Classification
No full textImage harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are mostly trained in a fully supervised manner, while demonstrating promising results, they do not generalize well to complex unseen cases involving significant style and semantic difference between the composited foreground object and the background image. In this paper, we present a self-supervised image harmonization framework that enables superior performance on complex cases. To do so, we first synthesize a large amount of data with wide diversity for training. We then develop an attentive harmonization module to adaptively adjust the foreground appearance by querying relevant background features. To allow more effective image harmonization, we develop a region-aware harmony classifier to explicitly judge whether an image is harmonious or not. Experiments on several datasets show that our method performs favourably against previous methods. Our code will be made publicly available.Computer Graphics ForumMajor Revision from Pacific Graphics44
An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes
No full textDigital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realistic RGB images of a 3D scene that align with the geometry of that scene. For appearance modeling, SVBRDF prediction networks recover material parameters from RGB images. Combining these technologies allows us to quickly generate SVBRDF maps for multiple views of a 3D scene, which can be merged to form a SVBRDF texture atlas of that scene. In this paper, we analyze the challenges and opportunities for SVBRDF prediction in the context of such a fast appearance modeling pipeline. On the one hand, single-view SVBRDF predictions might suffer from multiview incoherence and yield inconsistent texture atlases. On the other hand, generated RGB images, and the different modalities on which they are conditioned, can provide additional information for SVBRDF estimation compared to photographs. We compare neural architectures and conditions to identify designs that achieve high accuracy and coherence. We find that, surprisingly, a standard UNet is competitive with more complex designs.Eurographics Symposium on RenderingAppearance Modellin
Spatialization, fusion and enrichment of Multimodal Imaging for Interdisciplinary Digital Heritage Studies
No full textDigital Heritage (DH) has emerged as a dynamic and crucial concept for the future of Heritage Science (HS), at the crossroads of interdisciplinary fields. Nowadays, methods, tools and technologies for capturing reality play a predominant role in Cultural Heritage (CH) documentation framework. Indeed, the 2D/3D imaging and digitization techniques are massively employed today to survey, document, and study heritage artifacts. They offer numerous perspectives and avenues for investigation to enhance shared knowledge around heritage conservation and restoration. However, as the need for digital expertise expends in both scope and number, these various methods employed face the challenge of multimodality. This concept is at the core of this research, it is understood and justified by the growing need to cooperate with various digital resources (originating from multiple sensors, scales of observation, spectral or temporal layers) in order to feed and cross expertise. This paper explores 2D and 3D digitization strategies to enhance the potential of multimodal studies. The main contributions develop data-driven methods improving Spatialization, Fusion and Enrichment stages. Different types of approaches are proposed, aiming to better articulate the instrumental, computational and analytical phases in order to increase the informative potential of multi-source 2D/3D modelling. The strategy is demonstrated by a series of works and experiments enabling to construct and explore enriched multimodal data sets. The proposal offers reasoned and pragmatic solutions while the discussion anticipates emerging challenges such as semantic technologies, open science, artificial intelligence, and digital sobriety.Digital HeritageData Analysis, Datasets and Multimodal Approache
An Investigation of the Apple Vision Pro for Out-of-Core Ray-Guided Volume Rendering with BorgVR
No full textWe present an in-depth investigation of the Apple Vision Pro as a platform for large-scale volume visualization, focusing on both its technical capabilities and practical limitations in immersive rendering scenarios. Our study centers on BorgVR, a custom-built volume rendering system that implements a bricked, ray-guided, and out-of-core rendering pipeline tailored to the unique characteristics of the Vision Pro and the visionOS graphics stack. BorgVR is designed to overcome memory and performance bottlenecks associated with rendering structured grids that exceed device-local memory. Through dynamic data streaming, hierarchical bricking, GPU-accelerated early ray termination and empty-space skipping, the system achieves interactive frame rates for gigabyte-scale datasets, even under the constraints of mobile spatial computing. We analyze how well the Apple Vision Pro supports such workloads across its distinct rendering modes. Beyond demonstrating system performance, we evaluate the Vision Pro's suitability for scientific visualization-highlighting its strengths in display fidelity and sensor integration, while also documenting friction points such as GPU architecture constraints, memory management, and platform-specific development hurdles. The open-source release of BorgVR provides a reusable foundation for the community, facilitating future research and application development in immersive volume visualization.Vision, Modeling, and VisualizationVisualization, Visual Analytics, and V
Realistic Impact Method with Force Feedback in VR Space Using a Lower Limb Exoskeleton Device
No full textIn recent years, the widespread adoption of Head-Mounted Displays (HMDs) has made Virtual Reality (VR) experiences more accessible, leading to the development of force-feedback devices to enhance immersion. Force-feedback devices enhance VR immersion but presenting large, realistic forces, such as for a soccer kick, is challenging due to safety constraints. Therefore, designing the presented reaction force is crucial to enhance realism and mitigate perceptual discrepancies. In this study, we used a lower limb-mounted force-feedback device to investigate how different torque waveforms presented during a ball kick affect user perception.ICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments - Posters and DemosPosters and Demo
FRIDU: Functional Map Refinement with Guided Image Diffusion
No full textWe propose a novel approach for refining a given correspondence map between two shapes. A correspondence map represented as a functional map, namely a change of basis matrix, can be additionally treated as a 2D image. With this perspective, we train an image diffusion model directly in the space of functional maps, enabling it to generate accurate maps conditioned on an inaccurate initial map. The training is done purely in the functional space, and thus is highly efficient. At inference time, we use the pointwise map corresponding to the current functional map as guidance during the diffusion process. The guidance can additionally encourage different functional map objectives, such as orthogonality and commutativity with the Laplace-Beltrami operator. We show that our approach is competitive with state-of-the-art methods of map refinement and that guided diffusion models provide a promising pathway to functional map processing.Computer Graphics ForumShape Analysis44