Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
OctFusion: Octree-based Diffusion Models for 3D Shape Generation
No full textDiffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are guaranteed to be continuous and manifold. The key components of OctFusion are the octree-based latent representation and the accompanying diffusion models. The representation combines the benefits of both implicit neural representations and explicit spatial octrees and is learned with an octree-based variational autoencoder. The proposed diffusion model is a unified multi-scale U-Net that enables weights and computation sharing across different octree levels and avoids the complexity of widely used cascaded diffusion schemes. We verify the effectiveness of OctFusion on the ShapeNet and Objaverse datasets and achieve state-of-the-art performances on shape generation tasks. We demonstrate that OctFusion is extendable and flexible by generating high-quality color fields for textured mesh generation and high-quality 3D shapes conditioned on text prompts, sketches, or category labels. Our code and pre-trained models are available at https://github.com/octree-nn/octfusion.Computer Graphics ForumShape Segmentation and Texturing44
GaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splatting
No full textFluid simulation typically depends on manual modeling and visual assessment to achieve desired outcomes, which lacks objectivity and efficiency. To address this limitation, we propose GaussFluids, a novel approach for directly reconstructing temporally and spatially continuous Lagrangian fluid particles from videos. We employ a Lagrangian particle-based method instead of an Eulerian grid as it provides a direct spatial mass representation and is more suitable for capturing fine fluid details. First, to make discrete fluid particles differentiable over time and space, we extend Lagrangian particles with Gaussian probability densities, termed Gaussian Particles, constructing a differentiable fluid particle renderer that enables direct optimization of particle positions from visual data. Second, we introduce a fixed-length transform feature for each Gaussian Particle to encode pose changes over continuous time. Next, to preserve fundamental fluid physics-particularly incompressibility-we incorporate a density-based soft constraint to guide particle distribution within the fluid. Furthermore, we propose a hybrid loss function that focuses on maintaining visual, physical, and geometric consistency, along with an improved density optimization module to efficiently reconstruct spatiotemporally continuous fluids. We demonstrate the effectiveness of GaussFluids on multiple synthetic and real-world datasets, showing its capability to accurately reconstruct temporally and spatially continuous, physically plausible Lagrangian fluid particles from videos. Additionally, we introduce several downstream tasks, including novel view synthesis, style transfer, frame interpolation, fluid prediction, and fluid editing, which illustrate the practical value of GaussFluids.Pacific Graphics Conference Papers, Posters, and DemosPoint Clouds & Gaussian Splattin
Swiss Echoes: An immersive and embodied exploration of a national broadcasting archive
No full textThis paper answers the need for new modes of access for large audiovisual collections and builds on top of the computational and immersive turn of the cultural sector. The immersive installation Swiss Echoes fosters an embodied and spatialised paradigm in which visitors fly over a topographical 3D map of the Swiss landscape to discover how the voices captured in the national broadcasting archive of the Radio Télévision Suisse talk about local places. Through a reflection on the design rationale supported by key insights from a user evaluation conducted at our laboratory, three main themes are elucidated. First, the computational augmentation of the archive foregrounds access to a collection of locations rather than videos. Second, the use of an immersive environment and a performative controller fosters a profoundly embodied mode of spatial exploration. Third, sharing the immersive experience between multiple visitors creates a collective form of engagement, where the main visitor interacting becomes a performer and director for the others.Digital HeritageVisual Archives and Historical Imagery in V
PARC: A Two-Stage Multi-Modal Framework for Point Cloud Completion
No full textPoint cloud completion is vital for accurate 3D reconstruction, yet real world scans frequently exhibit large structural gaps that compromise recovery. Meanwhile, in 2D vision, VAR (Visual Auto-Regression) has demonstrated that a coarse-to-fine ''nextscale prediction'' can significantly improve generation quality, inference speed, and generalization. Because this coarse-to-fine approach closely aligns with the progressive nature of filling missing geometry in point clouds, we were inspired to develop PARC (Patch-Aware Coarse-to-Fine Refinement Completion), a two-stage multimodal framework specifically designed for handling missing structures. In the pretraining stage, PARC leverages complete point clouds alongside a Patch-Aware Coarse-to- Fine Refinement (PAR) strategy and a Mixture-of-Experts (MoE) architecture to generate high-quality local fragments, thereby improving geometric structure understanding and feature representation quality. During finetuning, the model is adapted to partial scans, further enhancing its resilience to incomplete inputs. To address remaining uncertainties in areas with missing structure, we introduce a dual-branch architecture that incorporates image cues: point cloud and image features are extracted independently and then fused via the MoE with an alignment loss, allowing complementary modalities to guide reconstruction in occluded or missing regions. Experiments conducted on the ShapeNet-ViPC dataset show that PARC has achieved highly competitive performance. Code is available at https://github.com/caiyujiaocyj/PARC.Computer Graphics ForumCreating and Processing Point Clouds44
When Dimensionality Reduction Meets Graph (Drawing) Theory: Introducing a Common Framework, Challenges and Opportunities
No full textIn the vast landscape of visualization research, Dimensionality Reduction (DR) and graph analysis are two popular subfields, often essential to most visual data analytics setups. DR aims to create representations to support neighborhood and similarity analysis on complex, large datasets. Graph analysis focuses on identifying the salient topological properties and key actors within network data, with specialized research investigating how such features could be presented to users to ease the comprehension of the underlying structure. Although these two disciplines are typically regarded as disjoint subfields, we argue that both fields share strong similarities and synergies that can potentially benefit both. Therefore, this paper discusses and introduces a unifying framework to help bridge the gap between DR and graph (drawing) theory. Our goal is to use the strongly math-grounded graph theory to improve the overall process of creating DR visual representations. We propose how to break the DR process into well-defined stages, discuss how to match some of the DR state-of-the-art techniques to this framework, and present ideas on how graph drawing, topology features, and some popular algorithms and strategies used in graph analysis can be employed to improve DR topology extraction, embedding generation, and result validation. We also discuss the challenges and identify opportunities for implementing and using our framework, opening directions for future visualization research.Computer Graphics ForumDimensionality Reduction and High-Dimensional Dat
Swept Volume Computation with Enhanced Geometric Detail Preservation
No full textSwept volume computation-the determination of regions occupied by moving objects-is essential in graphics, robotics, and manufacturing. Existing approaches either explicitly track surfaces, suffering from robustness issues under complex interactions, or employ implicit representations that trade off geometric fidelity and face optimization difficulties. We propose a novel inversion of motion perspective: rather than tracking object motion, we fix the object and trace spatial points backward in time, reducing complex trajectories to efficiently linearizable point motions. Based on this, we introduce a multi-field tetrahedral framework that maintains multiple distance fileds per element, preserving fine geometric details at trajectory intersections where single-field methods fail. Our method robustly computes swept volumes for diverse motions, including translations and screw motions, and enables practical applications in path planning and collision detection.Computer Graphics ForumShape Extraction44
Students Teaching Students Computer Art and Graphics
No full textWe explore and reflect on how a multi-generational computer science capstone project has led three cohorts of students to learn basic concepts from undergraduate computer graphics. We investigate how our project model has led students learning computer graphics to create valuable educational tools and examples for future students to further learn computer graphics. This self-perpetuation of student development has led students to invest their time and energy into the education of themselves and that of future students. Moreover, we find that computer graphics is especially well suited for this educational model.Eurographics 2025 - Education PapersEducation
H/RADIOSA: Recommended Approaches for the Development of Interoperable Open Semantic Artefacts in the Heritage Domain
No full textThis paper offers actionable recommendations and best practices for developing semantic artefacts in the Heritage field. Aimed at both experts and non-specialists, it highlights the importance of adopting FAIR and Linked Data principles. Drawing on a survey of existing tools and a review of relevant literature, the ‹H/RADIOSA› initiative proposes guidelines to bridge the gap between domain-specific needs and technical standards. These recommendations serve as a call to action for researchers and practitioners to foster the creation of high-quality, interoperable semantic artefacts.Digital HeritageInfrastructures, Platforms and Digital Ecosystem
A Preliminary Study of the Morphology and Spatial Distribution of Funerary Elements in the Southwestern Cemetery of Wadi al-Ma'awel, Oman
No full textThis study examines funerary morphologies and their spatial organization in the western and southwestern ceme- tery of Wadi al-Ma'awel, Oman, spanning the Wadi Suq and Iron Age periods. Using field surveys, remote sens- ing, and GIS analysis (Standard Deviation Ellipse method), we documented 185 funerary structures, primarily circular, rectangular, and ogival. Statistical analyses in R identified significant clustering related to cultural and environmental factors. Integrating these spatial indicators with geometric measurements in a random forest model significantly improved morphological classification accuracy. The results highlight the importance of spatial context in interpreting burial practices and provide a predictive framework for locating additional burial sites.Digital HeritagePredictive Analysis, AI, Simulation, and Novel Computational Method
Computational Design of Deployable Gridshells with Curved Elastic Beams
No full textDeployable gridshells are lightweight structures made of interconnected elastic beams. They can be actuated from a compact state to a freeform and volume-enclosing deployed shape. This thesis introduces C-shells, a novel class of deployable gridshells, which employs curved elastic rods connected at single-axis rotational joints. As opposed to their straight counterparts, C-shells are guaranteed to be assembled in a planar and stress-free configuration while showing a wide diversity in their deployed shapes. They may serve as temporary shelters, pavilions, or on a smaller scale, as deployable furniture or decorative elements.
This thesis presents a comprehensive framework for the forward exploration of C-shell designs, enabling designers to interactively search the shape space and generate deployable structures with diverse appearances and topologies. The framework combines human-interpretable manipulations of a reference linkage with an efÏcient physics-based simulation to predict the deployed shape and mechanical behavior of the structure. Preservation of the linkage deployability and smoothness of the edits are ensured through the use of conformal maps as design handles. The framework is implemented as a Rhino-Grasshopper plugin, providing visual and quantitative realtime feedback on the deployed state.
The inverse design of C-shells is also addressed, where the deployed shape is given, and the flat state of the structure is computed. This thesis introduces a two-step pipeline composed of a flattening method and a design optimization algorithm. The flattening algorithm is based on kinetic considerations underlying the deployment of C-shells. The method harmonizes a flat and a hypothetical deployed state constrained on a user-prescribed target surface. The flat beam layout is further adjusted to minimize the deviation of the deployed shape to the target surface while ensuring a low elastic energy deployed state, under some beam smoothness regularization. The proposed method is validated through scanned small-scale prototypes.
C-shells are made of curved rods, which entails additional material waste compared to straight beams. To address this issue, this thesis presents a rationalization method that splits the curved beams into smaller straight elements which can be grouped into a sparse kit of parts, while preserving user-provided designs. The original combinatorial problem of jointly assigning parts to elements and adapting the parts’ geometry is relaxed into a two-step optimization process incorporating our physics-based simulation, making it tractable using continuous optimization techniques. The proposed method applies more generally to bending-active structures and is further demonstrated on orthogonal gridshells and umbrella meshes. Part reuse is assessed in a study of the trade-off between the number of parts and fidelity to the input designs.EG Graphics Dissertation Onlin