Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
UV Parametrization via Topological Disk Segmentation of Surfaces
No full textWe present a reliable method for UV mapping that leverages a Voronoi-based decomposition of a triangulated surface mesh. Given a sparse set of sample points on the input shape, we construct the corresponding Voronoi partition and iteratively refine it to ensure that all regions are topologically equivalent to disks. The refinement proceeds in two stages: first, Voronoi cells are subdivided until disk-like topology is guaranteed; then, adjacent regions sharing substantial boundary portions are merged to reduce both their total number and perimeter-to-area ratio, while preserving disk equivalence. This topological guarantee enables straightforward and reliable UV parameterization. Our method exhibits an extremely low failure rate, making it suitable for practical use. In quantitative experiments on standard UV mapping benchmarks, we achieve performance comparable to state-of-the-art techniques. Furthermore, we analyze robustness and efficiency across different sampling densities, providing insights into the computational cost of each step of the pipeline.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceGeometry Processin
NeuroShape: exploiting neural architectures for shape analysis of ultrastructural 3D neuroscience morphologies
No full textRecent advances in volume electron microscopy (EM) enable nanometric-scale 3D reconstructions of neural tissue, providing unprecedented opportunities for studying cellular and subcellular morphology in neuroscience. The geometry of structures such as nuclei, neurites, and organelles can encode phenotypic information relevant to both functional specialization and pathological conditions, and thus represents a valuable complement to connectivity-based approaches in connectomics. While previous studies relied on handcrafted descriptors and classical machine learning for morphology analysis, recent progress in deep learning for 3D shape understanding offers new opportunities to learn robust, task-specific representations directly from geometric data. In this work we present NeuroShape, a first exploration of modern deep learning methods for shape analysis of ultrastructural 3D neuroscience morphologies. We introduce two annotated datasets derived from EM reconstructions: one of nuclei envelopes, and one of neurites and neural organelles. We benchmark two state-of-the-art neural architectures for 3D geometry (DiffusionNet [SACO22] and Laplacian2Mesh [DWL∗24]) and compare them against traditional feature-based descriptors previously used in neural morphology analysis. Our preliminary results highlight both the feasibility and the challenges of applying deep learning shape analysis techniques in this domain, and we release the datasets as a reference resource for future studies.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceDataset
High-Resolution 3D Shape Matching with Global Optimality and Geometric Consistency
No full text3D shape matching plays a fundamental role in applications such as texture transfer and 3D animation. A key requirement for many scenarios is that matchings exhibit geometric consistency, which ensures that matchings preserve neighbourhood relations across shapes. Despite the importance of geometric consistency, few existing methods explicitly address it, and those that do are either local optimisation methods requiring accurate initialisation, or are severely limited in terms of shape resolution, handling shapes with only up to 3,000 triangles. In this work, we present a scalable approach for geometrically consistent 3D shape matching that, for the first time, scales to high-resolution meshes with up to 10,000 triangles. Our method follows a two-stage procedure: (i) we compute a globally optimal and geometrically consistent mapping of surface patches on the source shape to the target shape via a novel integer linear programming formulation. (ii) we find geometrically consistent matchings of corresponding surface patches which respect correspondences of boundaries of patches obtained from stage (i). With this, we obtain dense, smooth, and guaranteed geometrically consistent correspondences between high-resolution shapes. Empirical evaluations demonstrate that our method is scalable and produces highquality, geometrically consistent correspondences across a wide range of challenging shapes. Our code is publicly available: https://github.com/NafieAmrani/SuPa-Match.Computer Graphics ForumShape Analysis44
Prototyper: a web3D platform for collaborative design and simulation of hybrid museum exhibitions
No full textHybrid Exhibition Design (HED) involves physical environments and digital layers (e.g. AR/VR, IoT, and web3D), introducing multidisciplinary complexity across curatorial, design, and technological domains. To address the need for flexible, scalable, and accessible Authoring Tools (AT) in this context, we propose a methodological framework based on layered abstraction (components, widgets, templates), aiming to streamline collaborative design and rapid prototyping. Applying this methodology within the ATON framework, we developed ''Prototyper'', a web-based 3D authoring platform that enables non-developers to design, configure, and simulate hybrid museum experiences. The Prototyper Minimum Viable Product (MVP) implements minimal but expandable features, including 3D model integration, semantic interaction mapping, spatial measurements, and viewpoint simulation within a widget-based architecture. Developed as a proof of concept within the H2IOSC Project, this work demonstrates the feasibility of empowering co-design processes, reducing technical bottlenecks, and supporting more iterative, multidisciplinary approaches to exhibition planning in Cultural Heritage (CH) contexts.Digital HeritageH2IOSC Project Developmen
DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization
No full textHigh-quality motion reconstruction that follows the user's movements can be achieved by high-end mocap systems with many sensors. However, obtaining such animation quality with fewer input devices is gaining popularity as it brings mocap closer to the general public. The main challenges include the loss of end-effector accuracy in learning-based approaches, or the lack of naturalness and smoothness in IK-based solutions. In addition, such systems are often finely tuned to a specific number of trackers and are highly sensitive to missing data, e.g., in scenarios where a sensor is occluded or malfunctions. In response to these challenges, we introduce DragPoser, a novel deep-learning-based motion reconstruction system that accurately represents hard and dynamic constraints, attaining real-time high end-effectors position accuracy. This is achieved through a pose optimization process within a structured latent space. Our system requires only one-time training on a large human motion dataset, and then constraints can be dynamically defined as losses, while the pose is iteratively refined by computing the gradients of these losses within the latent space. To further enhance our approach, we incorporate a Temporal Predictor network, which employs a Transformer architecture to directly encode temporality within the latent space. This network ensures the pose optimization is confined to the manifold of valid poses and also leverages past pose data to predict temporally coherent poses. Results demonstrate that DragPoser surpasses both IK-based and the latest data-driven methods in achieving precise end-effector positioning, while it produces natural poses and temporally coherent motion. In addition, our system showcases robustness against on-the-fly constraint modifications, and exhibits adaptability to various input configurations and changes. The complete source code, trained model, animation databases, and supplementary material used in this paper can be found at https://upc-virvig.github.io/DragPoserComputer Graphics ForumBringing Motion to Life: Motion Reconstruction and Control44
Formalising cultural heritage metadata with a multidisciplinary approach: enriching the CHANGES workflow for enhancing a museum collection about ceramics through a FAIR digitisation process
No full textThe domain of Galleries, Libraries, Archives and Museums is naturally rich in unstructured and semi-structured data, often collected favouring field-specific informative content to data Findability, Accessibility, Interoperability and Reusability. Intending to define a balanced pipeline for small-scale museums' metadata dissemination, this paper introduces Digital Damaged Ceramics, a multidisciplinary project aimed at leveraging digital tools and Open Science-oriented pipelines to formalise domain-specific knowledge about two collections of ceramic specimens, held by the Museo Internazionale delle Ceramiche in Faenza and the Musée National céramique de Sèvres. With a minimal setting of resources, the project could benefit from multidisciplinary solutions tailored within a limited team of researchers with complementary expertise covering digital skills and domain-specific knowledge, and from the state-of-the-art digitisation workflow developed by CHANGES project's Spoke 4, dedicated to Virtual technologies for museums and art Collections, within the framework of the National Recovery and Resilience Plan. The first part of the proposed methodology is experimental, meant to address and adequately visualise aspects specifically concerning the study of damaged ceramics. In the spirit of the best Open Science practices, the second phase consists of the re-adoption of a consolidated workflow, covering both metadata management and 3D digitisation process. All the research products are available online on a dedicated website, including: a data visualisation landing page, a catalogue for each of the two collections, an interface for semantically querying the dataset with SPARQL, a page for exposing 3D models, another one for the datasets, and a documentation.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
Neural Field Multi-view Shape-from-polarisation
No full textWe tackle the problem of multi-view shape-from-polarisation using a neural implicit surface representation and volume rendering of a polarised neural radiance field (P-NeRF). The P-NeRF predicts the parameters of a mixed diffuse/specular polarisation model. This directly relates polarisation behaviour to the surface normal without explicitly modelling illumination or BRDF. Via the implicit surface representation, this allows polarisation to directly inform the estimated geometry. This improves shape estimation and also allows separation of diffuse and specular radiance. For polarimetric images from division-of-focal-plane sensors, we fit directly to the raw data without first demosaicing. This avoids fitting to demosaicing artefacts and we propose losses and saturation masking specifically to handle HDR measurements. Our method achieves state-of-the-art performance on the PANDORA benchmark. We apply our method in a lightstage setting, providing single-shot face capture.Computer Graphics ForumDifferentiable Rendering44
From Steps to Verses: Following the Shared Journey of Language and the Body Through Wearable Technology
No full textThis study investigates a creative practice that uses bodily movement as linguistic input, departing from the efficiency-driven logic of traditional typing. The ''Keyboard Shoes'' embed mechanical switches in the soles, converting walking into letter inputs that map to Chinese characters for acrostic poem generation. Inspired by the legend of ''composing a poem within seven steps,'' the work reframes walking as poetic input, forging new links between language and motion. A minimal algorithm preserves ambiguity and openness, prioritizing the generative process over semantic control. This approach reimagines the relationship between language, writing, and the body through wearable technology.Pacific Graphics Conference Papers, Posters, and DemosPosters and Demo
XMTC: Explainable Early Classification of Multivariate Time Series in Reach-to-Grasp Hand Kinematics
No full textUsing multiple hand sensors, hand kinematics can be measured in Human-Computer Interaction (HCI) with the intention to predict the user's intention in a reach-to-grasp action, leading to multivariate time series data. Then, the goal is to classify the multivariate time series data, where the class shall be predicted as early as possible. To investigate the prediction evolution, detect and analyze challenging conditions, and identify the best trade-off between early prediction and prediction quality, we present XMTC. XMTC incorporates visualizations on accuracy over time, multivariate time series classification probabilities, confusion matrices, and partial dependence plots for a trustworthy classification production. We employ XMTC to real-world HCI data in multiple scenarios to achieve good early classifications, as well as insights into which conditions are easy to distinguish, which multivariate time series measurements impose challenges, and which features have the most impact.Vision, Modeling, and VisualizationVisualization, Visual Analytics, and V
Self-Supervised Humidity-Controllable Garment Simulation via Capillary Bridge Modeling
No full textSimulating wet clothing remains a significant challenge due to the complex physical interactions between moist fabric and the human body, compounded by the lack of dedicated datasets for training data-driven models. Existing self-supervised approaches struggle to capture moisture-induced dynamics such as skin adhesion, anisotropic surface resistance, and non-linear wrinkling, leading to limited accuracy and efficiency. To address this, we present SHGS, a novel self-supervised framework for humidity-controllable clothing simulation grounded in the physical modeling of capillary bridges that form between fabric and skin. We abstract the forces induced by wetness into two physically motivated components: a normal adhesive force derived from Laplace pressure and a tangential shear-resistance force that opposes relative motion along the fabric surface. By formulating these forces as potential energy for conservative effects and as mechanical work for non-conservative effects, we construct a physics-consistent wetness loss. This enables self-supervised training without requiring labeled data of wet clothing. Our humidity-sensitive dynamics are driven by a multi-layer graph neural network, which facilitates a smooth and physically realistic transition between different moisture levels. This architecture decouples the garment's dynamics in wet and dry states through a local weight interpolation mechanism, adjusting the fabric's behavior in response to varying humidity conditions. Experiments demonstrate that SHGS outperforms existing methods in both visual fidelity and computational efficiency, marking a significant advancement in realistic wet-cloth simulation.Computer Graphics ForumDigital Clothing44