Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
PhyDeformer: High-Quality Non-Rigid Garment Registration with Physics-Awareness
No full textAccurately registering 3D garment meshes to real-world image data is a fundamental yet challenging task in computer vision and graphics, with applications in virtual try-on systems, digital fashion, performance capture, and virtual content creation. This problem involves recovering detailed, non-rigid garment geometry from partial, noisy, and often ambiguous visual cues extracted from 2D or reconstructed 3D data. A key challenge lies in aligning garment templates with target shapes while preserving realistic fabric behavior and accommodating variations in body shape, garment fit, and pose. We present PhyDeformer, a new deformation method for high-quality garment mesh registration. It operates in two phases: In the first phase, a garment grading is performed to achieve a coarse 3D alignment between the mesh template and the target mesh, accounting for proportional scaling and fit (e.g. length, size). In the second phase, the graded mesh is refined to capture fine-grained geometric details of the 3D target through a localized optimization process, leveraging a Jacobian-based deformation framework. Both quantitative and qualitative evaluations on synthetic and real garment data demonstrate the effectiveness and robustness of our method in achieving accurate and visually plausible registrations. The code and base meshes generated and evaluated in this paper are available at https://github.com/MLMS-CG/PhyDeformer.Eurographics Workshop on 3D Object RetrievalShort Paper
Too Heart to Handle? Exploring Self-Directed And Collaborative Virtual Learning Environments in Anatomy Education.
No full textThe integration of Extended Reality (XR) into medical education represents a transformative shift, particularly in anatomy training, where immersive simulations enhance cognitive engagement and knowledge retention. The developing heart is characterized by rapid morphological changes within a short time frame, which poses a significant pedagogical challenge. Conventional 2D imaging and static models often fail to convey these processes, limiting learners' ability to conceptualize critical spatial relationships-a barrier in understanding congenital anomalies. To address these limitations, this work leverages XRdriven visualization and interaction paradigms to create virtual learning environments. Based on this, we propose methods for designing XR educational modules that adapt to both collaborative and self-directed learning contexts, using embryonic cardiogenesis as an illustrating case study. We present findings from mixed-methods user studies involving a total of 264 students, along with feedback from lecturers, highlighting the importance of an iterative, user-centered design approach.EuroVis 2025 - Dirk Bartz Prize2nd Priz
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
No full textWe present a study of how to integrate color (RGB) and multi-spectral imagery (red, green, red-edge, and near-infrared) into the 3D Gaussian Splatting (3DGS) framework - a state-of-the-art explicit radiance-field-based method for fast and high-fidelity 3D reconstruction from multi-view images [KKLD23]. While 3DGS excels on RGB data, naïve per-band optimization of additional spectra yields poor reconstructions due to inconsistently appearing geometry in the spectral domain. This problem is prominent, even though the actual geometry is the same, regardless of spectral modality. To investigate this, we evaluate three strategies: 1) Separate per-band reconstruction with no shared structure; 2) Splitting optimization, in which we first optimize RGB geometry, copy it, and then fit each new band to the model by optimizing both geometry and band representation; and 3) Joint, in which the modalities are jointly optimized, optionally with an initial RGB-only phase. We showcase through quantitative metrics and qualitative novel-view renderings on multi-spectral datasets the effectiveness of our dedicated optimized Joint strategy, increasing overall spectral reconstruction as well as enhancing RGB results through spectral cross-talk. We therefore suggest integrating multi-spectral data directly into the spherical harmonics color components to compactly model each Gaussian's multi-spectral reflectance. Moreover, our analysis reveals several key trade-offs in when and how to introduce spectral bands during optimization, offering practical insights for robust multi-modal 3DGS reconstruction. The project page and code is located at: meyerls.github.io/towards_multi_spec_splatVision, Modeling, and VisualizationImaging and Image Processin
Resolving Self-intersections in 3D Meshes while Preserving Floating-point Coordinates
No full textWe present a straightforward and robust method for resolving the mesh intersection problem. We focus specifically on the challenge caused by the intersections resulting from the conversion of the vertices coordinates from their exact mathematical values to a fixed-precision floating-point format. Our method takes as input a soup of triangles and outputs intersection-free models whose vertices coordinates are all represented with double-precision floating-point format. We evaluated our approach thoroughly, considering a large collection of meshes. In particular, we can process all the 4 524 models in Thingi10K [ZJ16] that contain self-intersections. This outperforms previous state-of-the-art approaches: On the 527 models of Thingi10K for which naive rounding fails, Zhou et al.'s approach [ZGZJ16] is capable of handling 91% of them, and Valque's 94% [Val24]. In terms of time efficiency, our approach handles about 50k vertices per second on average, which is faster to that of Zhou et al. by a factor 1.4 on these non-trivial models and is faster than that of Valque by several order of magnitude.Computer Graphics ForumMesh Processing44
Skeletal Gesture Recognition Based on Joint Spatio-Temporal and Multi-Modal Learning
No full textHand skeleton-based gesture recognition is a crucial task in human-computer interaction and virtual reality. It aims to achieve precise classification by analyzing the spatio-temporal dynamics of skeleton joints. However, existing methods struggle to effectively model highly entangled spatio-temporal features and fuse heterogeneous Joint, Bone, and Motion (J/B/JM) modalities. These limitations hinder recognition performance. To address these challenges, we propose an Adaptive Spatio-Temporal Network (ASTD-Net) for gesture recognition. Our approach centers on integrated spatio-temporal feature learning and collaborative optimization. First, for spatial feature learning, we design an Adaptive Multi-Subgraph Convolution Module (AMS-GCN) which mitigates spatial coupling interference and enhances structural representation. Subsequently, for temporal feature learning, we introduce a Multi-Scale Dilated Temporal Fusion Module (MD-TFN) that captures multi-granularity temporal patterns, spanning local details to global evolution. This allows for comprehensive modeling of temporal dependencies. Finally, we propose a Self-Supervised Spatio-Temporal Channel Adaptation Module (SSTC-A). Using a temporal discrepancy loss, SSTC-A dynamically optimizes cross-modal dependencies and strengthens alignment between heterogeneous J/B/JM features, enhancing their fusion. On the SHREC'17 and DHG-14/28 datasets, ASTD-Net achieves recognition accuracies of 97.50% and 93.57%, respectively. This performance surpasses current state-of-the-art methods by up to 0.50% and 1.07%. These results verify the effectiveness and superiority of our proposed method.Pacific Graphics Conference Papers, Posters, and DemosDetecting & Estimating from image
Computational Design of Body-Supporting Assemblies
No full textA body-supporting assembly is an assembly of parts that physically supports a human body during activities like sitting, lying, or leaning. A body-supporting assembly has a complex global shape to support a specific human body posture, yet each component part has a relatively simple geometry to facilitate fabrication, storage, and maintenance. In this paper, we aim to model and design a personalized body-supporting assembly that fits a given human body posture, aiming to make the assembly comfortable to use. We choose to model a body-supporting assembly from scratch to offer high flexibility for fitting a given body posture, which however makes it challenging to determine the assembly's topology and geometry. To address this problem, we classify parts in the assembly into two categories according the functionality: supporting parts for fitting different portions of the body and connecting parts for connecting all the supporting parts to form a stable structure. We also propose a geometric representation of supporting parts such that they can have a variety of shapes controlled by a few parameters. Given a body posture as input, we present a computational approach for designing a body-supporting assembly that fits the posture, in which the supporting parts are initialized and optimized to minimize a discomfort measure and then the connecting parts are generated using a procedural approach. We demonstrate the effectiveness of our approach by designing body-supporting assemblies that accommodate to a variety of body postures and 3D printing two of them for physical validation.Computer Graphics ForumShape Extraction44
The Secret of Bastet: Integrating VR and 3D Printing for the Study and Exhibition of a Cat Mummy
No full textThis paper presents the design and evaluation of a twofold dissemination experience to enhance the scientific study of a cat mummy. The mummy is part of the archaeological collection of an art museum. It has undergone scientific analysis, resulting in a large amount of digital data collected via X-ray, CT and photogrammetry, leading to significant discoveries about the nature and history of the mummy. The first part of the dissemination approach resulted in the production of a 1:1 scale transparent copy, which gives visitors a clear view of the mummy's contents. It has joined the museum's collection and is now displayed alongside the original mummy. The object is both aesthetic and scientific. It was produced using an advanced 3D printing technique based on 3D data generated from segmentations of CT scan data. The second part consists of a VR-based experience proposed to the museum's visitors, highlighting the scientific process that has led to new knowledge and unresolved questions. The VR environment guides users through data production, exploration and analysis, enhancing interpretation. This VR experience was first showcased at an international XR event, and later at the museum's weekly events. Two user studies were conducted on these occasions, using subjective questionnaires to gather feedback. The first assessed the presence, usability and comfort of the VR experience. The second assessed the impact on dissemination. The results show a strong user interest in the scientific approach and confirm the public interest in this method. The experience is now routinely offered in the museum.Digital HeritageStorytelling and Interpretation in Digital Heritag
A Design Space for the Critical Validation of LLM-Generated Tabular Data
No full textLLM-generated tabular data is creating new opportunities for data-driven applications in academia, business, and society. To leverage benefits like missing value imputation, labeling, and enrichment with context-aware attributes, LLM-generated data needs a critical validation process. The number of pioneering approaches is increasing fast, opening a promising validation space that, so far, remains unstructured. We present a design space for the critical validation of LLM-generated tabular data with two dimensions: First, the Analysis Granularity dimension-from within-attribute (single-item and multi-item) to acrossattribute perspectives (1×1, 1×m, and n×n). Second, the Data Source dimension-differentiating between LLM-generated values, ground truth values, explanations, and their combinations. We discuss analysis tasks for each dimension cross-cut, map 19 existing validation approaches, and discuss the characteristics of two approaches in detail, demonstrating descriptive power.EuroVis Workshop on Visual Analytics (EuroVA)Best Pape
DPV (Domain, Purpose, Visual) Framework: A data visualization design pedagogical method for middle schoolers
No full textData visualization literacy is essential for K-12 students, yet existing practices emphasize interpreting pre-made visualizations rather than creating them. To address this, we developed the DPV (Domain, Purpose, Visual) framework, which guides middle school students through the visualization design process. The framework simplifies design into three stages: understanding the problem domain, specifying the communication purpose, and translating data into effective visuals. Implemented in a twoweek summer camp as a usage scenario, the DPV framework enabled students to create visualizations addressing community issues. Evaluation of student artifacts, focus group interviews, and surveys demonstrated its effectiveness in enhancing students' design skills and understanding of visualization concepts. This work highlights the DPV framework's potential to foster data visualization literacy for K-12 education and broaden participation in the data visualization community.EuroVis 2025 - Education PapersEducation Papers Session
SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing
No full textNeural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model highlevel semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.Pacific Graphics Conference Papers, Posters, and DemosShape Extraction or Editin