Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
No full textPoint cloud denoising task aims to recover the clean point cloud from the scanned data coupled with different levels or patterns of noise. The recent state-of-the-art methods often train deep neural networks to update the point locations towards the clean point cloud, and empirically repeat the denoising process several times in order to obtain the denoised results. It is not clear how to efficiently arrange the iterative denoising processes to deal with different levels or patterns of noise. In this paper, we propose an adaptive and iterative point cloud denoising method based on the score-based diffusion model. For a given noisy point cloud, we first estimate the noise variation and determine an adaptive denoising schedule with appropriate step sizes, then invoke the trained network iteratively to update point clouds following the adaptive schedule. To facilitate this adaptive and iterative denoising process, we design the network architecture and a two-stage sampling strategy for the network training to enable feature fusion and gradient fusion for iterative denoising. Compared to the state-of-the-art point cloud denoising methods, our approach obtains clean and smooth denoised point clouds, while preserving the shape boundary and details better. Our results not only outperform the other methods both qualitatively and quantitatively, but also are preferable on the synthetic dataset with different patterns of noises, as well as the real-scanned dataset.Computer Graphics ForumOriginal Article44
Body-Scale-Invariant Motion Embedding for Motion Similarity
No full textAccurate measurement of motion similarity is crucial for applications in healthcare, rehabilitation, sports analysis, and human- computer interaction. However, existing Human Pose Estimation (HPE) approaches often conflate motion dynamics with anatomical variations, leading to body-scale-dependent similarity assessments. We propose a framework for learning bodyscale- invariant motion embeddings directly from RGB videos. Leveraging diverse 3D character animations with varied skeletal proportions, we generate standardized motion data and train the SAME model to capture temporal dynamics independent of body size. Our approach enables robust cross-character motion similarity evaluation. Experimental results show that the method effectively decouples kinematic patterns from structural differences, outperforming scale-sensitive baselines. Key contributions include: (1) a scalable motion data processing pipeline; (2) a learning-based body-scale-invariant embedding method; and (3) validation of motion similarity assessment independent of anatomy.Pacific Graphics Conference Papers, Posters, and DemosPosters and Demo
A Lightweight 3D Gaussian Splatting Based Virtual Object Insertion Strategy for Casually Captured Scenes
No full textThe physically plausible insertion of virtual objects into scenes captured by multi-view images can be applied to multiple domains such as urban planning, augmented reality and digital marketplaces. Recent advancements in Novel View Synthesis, such as 3D Gaussian Splatting provide photorealistic representations of casually captured scenes. This raises the question if these advancements can be incorporated into the virtual insertion of single objects. In this work, we propose a lightweight strategy that estimates the effects of light interaction between a virtually inserted mesh model with corresponding material properties and a scene represented as 3D Gaussian Splats. Our approach poses minimal constraints on the capturing setup, only relying on casually captured LDR multi-view scenes, i.e., by a smartphone, while demonstrating comparable visual fidelity to strategies that pose more constraints on the capturing process.Computer Graphics and Visual Computing (CGVC)Geometry, Rendering, Animatio
Happiness Finder: Exploring User Experience in AI-Assisted Four-Leaf Clover Searches
No full textThe rare four-leaf clover (FLC) is regarded worldwide as a symbol of good luck. However, it is not easy to find one among the common three-leaf clovers. This study explores how people feel when technological intervention is introduced to assist in identifying FLC. We investigated user experiences during outdoor searches supported by an object detection algorithm. Our results showed no significant difference in the impact of technological intervention on users' positive emotions; however, the findings suggest that such intervention may play a supportive role.ICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments - Posters and DemosPosters and Demo
Generative AI and the Narrative Turn in Digital Cultural Heritage Education
No full textThis panel explores how generative AI transforms higher education teaching, design, and evaluation of interactive digital narratives (IDNs) in cultural heritage. Bringing together scholars from museology, digital heritage, game design, creative computing, and educational technology, it examines AI's impact on pedagogy, authorship, and interpretive authority. The discussion focuses on three themes: AI as a disruptor of traditional humanities education, its potential for collaborative narrative co-creation, and the need for new evaluation frameworks grounded in ethics and critical literacy. Addressing both institutional resistance and inevitable change, the panel aims to foster dialogue around inclusive, reflective, and ethically grounded approaches to AI-enhanced cultural storytelling.Digital HeritagePanels, Roundtable
One-Shot Method for Computing Generalized Winding Numbers
No full textThe generalized winding number is an essential part of the geometry processing toolkit, allowing to quantify how much a given point is inside a surface, even when the surface has boundaries and noise. We propose a new universal method to compute a generalized winding number, based only on the surface boundary and the intersections of a single ray with the surface, supporting any oriented surface representations that support a ray intersection query. Due to the focus on the boundary, our algorithm has a unique set of properties. For 2D parametric curves, on a regular grid of query points, our method is up to 4× faster than the current state of the art, maintaining the same precision. In 3D, our method can compute a winding number of a surface without discretizing it, including parametric surfaces. For some meshes with many triangles and a simple boundary, our method is faster than the hierarchical evaluation of the generalized winding number while still being precise. Similarly, on some parametric surfaces with a simple boundary, our method can be faster than adaptive quadrature. We validate our algorithms theoretically, numerically, and by demonstrating a gallery of results on a variety of parametric surfaces and meshes, as well uses in a variety of applications, including voxelizations and boolean operations.Computer Graphics ForumImplicit Representations44
Q-ART Owen Scrambling
No full textOwen scrambling is a standard randomization technique for common sampling distributions used in quasi-Monte-Carlo applications such as rendering. We extend the recently introduced binary-based ART-Owen scrambling to the base-4 case, covering the full 4! permutations while still maintaining the method's simple and elegant structure. We achieve this by decomposing the permutation space into an affine transformation, enabling compact encoding and efficient processing.Computer Graphics and Visual Computing (CGVC)Short Papers Session: Games and Graphic
Morphosyntactic Variation in Italian and Romansh Dialects: The Manzini & Savoia (2005) Corpus Within Project CHANGES
No full textThis paper presents the digitization and online dissemination of the Manzini & Savoia (2005) corpus, one of the most comprehensive resources on morphosyntactic variation in Italian and Romansh dialects. Developed within Project CHANGES (Cultural Heritage Active Innovation for Sustainable Society), the initiative responds to the urgent need for systematic documentation and open-access preservation of linguistic diversity. The new platform integrates a relational PostgreSQL database, a Strapi-based backend, and an interactive web interface, offering multiple modes of exploration-including map-based navigation, morphosyntactic query, and access to original fieldwork notebooks. The entire dataset (64,472 examples with IPA transcription and metadata) is openly available on Zenodo for independent research and reuse. The project also explores experimental applications of Large Language Models (LLMs) for automatic annotation, demonstrating the potential for computational approaches in dialectology. This work provides a replicable model for sustainable digital archiving and fosters interdisciplinary research across linguistic, computational, and cultural heritage domains.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
Visualization, Virtualization, and 3D Data Analysis in the Historical (Re) Construction of Household, Village, and Regional Landscapes: The Mount Amiata-Maremma Digital Heritage Project
No full textBuilding on the seminal Mt. Amiata Project, the innovative Emptyscapes Project, and the initial work of Global Digital Heritage (GDH)) in southern Tuscany, a new form of transdisciplinary research is being developed. This project will transform the documentation, interpretation, and dissemination of the region's rich archaeological and historical heritage through interdisciplinary methodologies and the integration of advanced digital tools, including remote sensing, GIS, photogrammetry, and 3D visualization. This paper outlines the project's multi-scalar and diachronic approach to heritage analysis, emphasizing the interaction between digital technologies, historical reconstruction, and local community participation.Digital HeritageFrom 3D Models to Digital Platforms and Digital Twin
Multi-Modal Instrument Performances (MMIP): A Musical Database
No full textMusical instrument performances are multimodal creative art forms that integrate audiovisual elements, resulting from musicians' interactions with instruments through body movements, finger actions, and facial expressions. Digitizing such performances for archiving, streaming, analysis, or synthesis requires capturing every element that shapes the overall experience, which is crucial for preserving the performance's essence. In this work, following current trends in large-scale dataset development for deep learning analysis and generative models, we introduce the Multi-Modal Instrument Performances (MMIP) database (https://mmip.cs.ucy.ac.cy). This is the first dataset to incorporate synchronized high-quality 3D motion capture data for the body, fingers, facial expressions, and instruments, along with audio, multi-angle videos, and MIDI data. The database currently includes 3.5 hours of performances featuring three instruments: guitar, piano, and drums. Additionally, we discuss the challenges of acquiring these multi-modal data, detailing our approach to data collection, signal synchronization, annotation, and metadata management. Our data formats align with industry standards for ease of use, and we have developed an open-access online repository that offers a user-friendly environment for data exploration, supporting data organization, search capabilities, and custom visualization tools. Notable features include a MIDI-to-instrument animation project for visualizing the instruments and a script for playing back FBX files with synchronized audio in a web environment.Computer Graphics ForumBringing Motion to Life: Motion Reconstruction and Control44