Computer Animation and Virtual Worlds最新文献

{"title":"Development and Validation of a Virtual Reality-Driven Interactive Digital Craft Modeling System","authors":"Hong Li,&nbsp;JiFeng Shen,&nbsp;Zheyu Zhang,&nbsp;Jiabin Wei,&nbsp;Guanghui Huang","doi":"10.1002/cav.70174","DOIUrl":"https://doi.org/10.1002/cav.70174","url":null,"abstract":"<div>\u0000 \u0000 <p>With the development of immersive technologies such as virtual reality, digital craft has shifted from static documentation to interactive reconstruction. This study presents a VR-based ceramic creation system developed in Unreal Engine, integrating surface-of-revolution modeling, constructive solid geometry, and dynamic mesh export to support real-time ceramic manipulation and a complete craft workflow. A user study involving 50 participants was conducted to evaluate system experience. Behavioral and questionnaire results show that users provided generally positive evaluations and were able to complete basic ceramic-making tasks after minimal instruction, indicating effective support for novice interaction. However, limitations remain in fine-grained manipulation, spatial orientation, and interaction precision due to constraints in haptic feedback and navigation design. Based on prototype validation and experimental results, this study proposes a design and implementation framework for virtual craft systems, covering system architecture, module division, technical design, interaction logic, development process, user performance optimization, and system scalability and sustainability, providing a scalable reference for digital heritage preservation, craft education, and cultural innovation. The study emphasizes process-oriented design, the balance of creativity and control, real-time responsiveness, and embodied procedural engagement as key to craft learning and interactive cultural reconstruction.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148616441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Human-Avatar Symbiosis to AI-Avatar Autonomy: Ethical Shifts in Virtual Reality (VR)","authors":"Aydın Bulut,&nbsp;Mehmet Koray Serin","doi":"10.1002/cav.70172","DOIUrl":"https://doi.org/10.1002/cav.70172","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid convergence of virtual reality (VR) and artificial intelligence (AI) has resulted in a redefined ethical framework for digital interaction. As AI-driven avatars gain cognitive and emotional autonomy, they transition from passive representations to active participants capable of shaping moral reasoning, social behavior, and value construction. The present study explores the ethical transformations that are emerging from this integration, focusing on how human-machine interaction reconfigures traditional concepts of responsibility, agency, and moral judgment. By employing a systematic and thematic analysis of the extant literature, the research identifies key trends such as the shift from user-centred ethics towards distributed and relational ethical systems embedded within technological frameworks. The findings indicate that immersive environments exert a significant influence on users' empathy and moral sensitivity, concomitantly giving rise to novel dilemmas pertaining to authenticity, consent, and algorithmic accountability. The study posits that the evolution from human–avatar symbiosis to AI–avatar autonomy signifies a fundamental transformation in the nature of ethical engagement within virtual ecosystems. These insights emphasize the necessity for inclusive, transparent, and value-sensitive approaches to guide the design and governance of future AI-integrated VR environments.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MGGAN: Learning a Multiscale Graph-Based GAN for Non-Parametric 3D Single-Shape Deformation and Variation","authors":"Jorge Jabón,&nbsp;Sergio Corbera,&nbsp;Rafael Barea","doi":"10.1002/cav.70169","DOIUrl":"https://doi.org/10.1002/cav.70169","url":null,"abstract":"<p>Shape variation and deformation play a central role in computer animation, digital content creation and geometry processing, a domain that has undergone significant advances in the past decade owing to deep-learning emergence. Most methods typically rely on large datasets or intermediate representations defined on Euclidean domains or grid-like structures. As a result, learning expressive deformation models directly from surface-based representations with limited data remains challenging. In this article, we present an unconditional learning-based framework that captures the internal geometric statistics of a single 3D triangle mesh to generate smooth deformations ranging from local variations to larger-scale shape changes across multiple spatial resolutions. The proposed Multiscale Graph-based Generative Adversarial Network (MGGAN) consists of a pyramid of generators and discriminators built using spectral and spatial graph operators, trained directly on the input mesh and its downsampled versions with Gaussian noise injected at each scale. By operating directly on the input mesh, the method produces visually coherent, smooth and topology-preserving deformed instances that are well suited for shape variation and asset exploration in animation and graphics pipelines.</p>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cav.70169","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Playing in Perfect Time: A Method for Synchronizing Scores, Avatars, and Game Elements With Precision","authors":"Katya Alvarez-Molina,&nbsp;Juan Martínez-Miranda,&nbsp;Rodrigo Garduño Linares,&nbsp;Ana Isabel Martínez-García,&nbsp;Karina Caro","doi":"10.1002/cav.70165","DOIUrl":"https://doi.org/10.1002/cav.70165","url":null,"abstract":"<div>\u0000 \u0000 <p>Sensorimotor synchronization (SMS) supports not only music and dance but also reading, language acquisition, and sports performance. Neurological and developmental conditions such as Parkinson's disease, dyslexia, or ADHD can impair SMS, limiting motor coordination and cognitive abilities. Rhythm-based video games provide a motivated interactive training tool for clinical contexts. However, commercial rhythm games often have problems with timing accuracy, overly broad response windows, and a lack of feedback, which makes them less useful for therapy or research. This work introduces a method designed to achieve precise synchronization in rhythm games. The method enables the translation of music scores into a component field in the Unity Inspector and generates game elements and interaction windows aligned with auditory cues and avatar movement. The method addresses existing limitations by ensuring strict response windows, accurate input logging, and balanced audiovisual integration. Evaluation against theoretical onset times showed a small and stable synchronization error (mean error = 5.164 ms, RMSE = 5.697 ms, median shift = 5.200 ms), supporting the timing accuracy of the proposed system. It provides a robust foundation for rhythm games supporting training, rehabilitation, and education.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mamba-Enhanced Graph Convolutional Network for Skeleton-Based Stereoscopic Hand Gesture Recognition in Augmented Reality","authors":"Fucheng Wan,&nbsp;Jian Teng","doi":"10.1002/cav.70164","DOIUrl":"https://doi.org/10.1002/cav.70164","url":null,"abstract":"<div>\u0000 \u0000 <p>Skeleton-based hand gesture recognition in augmented reality (AR) environments demands models that are both accurate and computationally efficient to support real-time stereoscopic interaction. Existing graph convolutional network (GCN) approaches construct dynamic adjacency matrices primarily through simple pairwise subtraction between joints, which constrains their capacity to capture the nuanced spatiotemporal dependencies inherent in stereoscopic AR gesture data. Furthermore, many current architectures impose substantial parameter overhead, thereby limiting deployment on resource-constrained AR devices. To address these challenges, this paper proposes a Mamba-Enhanced Graph Convolutional Network (ME-GCN), which integrates the selective state space model (SSM) Mamba into a lightweight graph convolutional framework for stereoscopic hand gesture recognition. Specifically, we design a Spatial Graph Mamba Module (SGMM) that leverages the linear-complexity temporal scanning capability of Mamba to model long-range inter-frame dependencies, and a Stereoscopic Depth-Aware Topology Refinement (SDTR) mechanism that dynamically adjusts the graph topology using binocular depth cues. A Channel-Temporal Dual-Stream Fusion (CTDF) strategy further integrates spatial, temporal, and depth features into a unified representation. Extensive experiments conducted on the SHREC'17 Track, DHG-14/28, and a custom AR-Stereo-Gesture dataset demonstrate that ME-GCN achieves competitive recognition accuracy while maintaining significantly fewer parameters and lower inference latency compared to state-of-the-art methods. Specifically, ME-GCN attains recognition accuracies of 97.38% and 94.16% on the SHREC'17 Track 14-class and 28-class tasks, and 94.28% and 92.14% on DHG-14/28, while requiring only 0.68 M parameters and 1.08 GFLOPs—a 48.5% parameter reduction relative to TD-GCN—at an average inference latency of 11.52 ms, the lowest among all compared methods. Future research will extend ME-GCN to continuous gesture recognition in streaming AR scenarios, multi-modal RGB-depth fusion, and lightweight model-compression techniques for real-time on-device AR deployment.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Usability and User Engagement of Herbal Heritage as a Medium for Gamified Learning of Kenyah and Kayan Traditional Medicinal Knowledge Using Extended Reality","authors":"Ally Dian Hendrick,&nbsp;Suriati Khartini Jali,&nbsp;Nurul Farizah Ridzuan,&nbsp;Jane Labadin,&nbsp;Abby Lian Hendrick,&nbsp;Mohd Harith Syazwan Samsawi","doi":"10.1002/cav.70167","DOIUrl":"https://doi.org/10.1002/cav.70167","url":null,"abstract":"<div>\u0000 \u0000 <p>Indigenous knowledge of traditional medicine, which has sustained Borneo's ethnic tribes for generations, is facing extinction due to the preference for modern medicine and a lack of motivation to pass down this wisdom. To combat this potential loss, this study explored the usability and user engagement of a smartphone-based extended reality application, Herbal Heritage, a gamified learning tool for Kenyah and Kayan medicinal practices. The study employed a mixed-methods approach to identify which gamification elements would best motivate users when utilizing augmented reality (AR) and non-immersive virtual reality (VR). Data collection methods included a post-test questionnaire that used the System Usability Scale (SUS), Intrinsic Motivation Inventory (IMI), observations, and open-ended interviews. The data collection was conducted at the FORUM Cultural Centre, Miri, with the Kenyah and Kayan communities. It found that a unified device offering both gamified AR and VR experiences was well-received by the community. The final prototype was highly successful, with participants deeming the immersive, gamified elements a valuable and effective means of preserving this indigenous knowledge.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction","authors":"Nathan Salazar,&nbsp;Emmanuel Dellandréa,&nbsp;Mathieu Lefort,&nbsp;Alexandre Meyer","doi":"10.1002/cav.70156","DOIUrl":"https://doi.org/10.1002/cav.70156","url":null,"abstract":"<p>Large-scale human motion datasets are essential for training robust motion models for analysis, synthesis, and understanding. While marker-based motion capture provides precise data, it is costly and limited in scale and diversity. Recent advances in monocular motion capture and video-language understanding open the way to extract plausible motion from unconstrained online videos. We present a scalable pipeline for constructing in-the-wild human motion datasets. From a few keywords, the system retrieves videos, extracts 3D body and facial motion, and generates high-level textual descriptions. The pipeline is flexible, enabling targeted collection of various motions, multi-person interactions, or expressive behaviors. We demonstrate its quality by training motion reconstruction and motion generation models, showing performance approaching that of models trained on traditional motion capture datasets, along with strong cross-dataset generalization. Code and motion data are available at \u0000https://github.com/NatSalaz/xmopipe.</p>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cav.70156","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NeuroSonic: Instant Neural Impact Sound Synthesis With Learned Acoustic Transfer","authors":"Junhan Zhao,&nbsp;Yiming Huang,&nbsp;Xutong Jin,&nbsp;Fei Zhu,&nbsp;Meng Gai,&nbsp;Sheng Li","doi":"10.1002/cav.70162","DOIUrl":"https://doi.org/10.1002/cav.70162","url":null,"abstract":"<div>\u0000 \u0000 <p>Physically based modal sound synthesis generates realistic audio by modeling structural vibration and acoustic radiation from object geometry and material properties. However, traditional approaches rely on computationally expensive eigenvalue analysis and acoustic transfer simulations, making them impractical for real-time virtual reality (VR), especially for dynamically generated or fractured objects. We present NeuroSonic, a unified neural framework for real-time physically based sound synthesis directly from point cloud geometry. Our key idea is to amortize modal analysis and acoustic transfer using neural networks, replacing costly numerical solvers with efficient feed-forward inference. The framework predicts modal eigenvalues, eigenvectors, and acoustic transfer functions, forming a physically grounded representation for sound synthesis. By operating on point clouds, our method avoids voxelization artifacts and handles geometrically complex and thin structures. Once trained, NeuroSonic computes complete modal and acoustic information in under 0.02 s, enabling real-time performance. Experiments show that our approach achieves accuracy comparable to physically based solvers while providing orders-of-magnitude speedup, making it a practical solution for interactive VR environments.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DESTalker: Disentangling Emotion and Style for Expressive 3D Facial Animation via Residual Generation","authors":"Xu Yang,&nbsp;Shiguang Liu,&nbsp;Qing Xu","doi":"10.1002/cav.70127","DOIUrl":"https://doi.org/10.1002/cav.70127","url":null,"abstract":"<div>\u0000 \u0000 <p>Speech-driven 3D facial animation has achieved remarkable lip-synchronization. However, generating expressive and personalized animations remains a formidable challenge. Existing methods often struggle with the entanglement of emotion and speaking style, as well as semantic conflicts arising from multi-modal inputs. To address these limitations, we propose <i>DESTalker</i>, a framework that disentangles emotion and style to generate expressive facial motion via residual modulation. We introduce an information-theoretic disentanglement strategy utilizing mutual information minimization and orthogonal constraints to robustly separate audio content, motion emotion, and speaking style. Furthermore, we adopt a residual generation strategy where neutral lip-sync motion is synthesized first, followed by the injection of emotion and style as residual components to preserve articulatory precision. Finally, to resolve cross-modal conflicts, we design a semantic consistency-guided soft-gating mechanism that dynamically regulates visual emotion integration under audio dominance. Extensive experiments on the 3DMEAD dataset demonstrate that DESTalker outperforms state-of-the-art methods in emotional expressiveness, style consistency, and lip-synchronization accuracy.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From SVG to DSVG: Leveraging Foveal Visual Cues to Mitigate Cybersickness in Redirected Walking","authors":"Xinda Liu,&nbsp;Yongbo Tang,&nbsp;Xiaoning Liu,&nbsp;Pengbo Zhou,&nbsp;Guohua Geng","doi":"10.1002/cav.70145","DOIUrl":"https://doi.org/10.1002/cav.70145","url":null,"abstract":"<div>\u0000 \u0000 <p>Redirected Walking (RDW) effectively extends the navigable area of virtual environments but frequently induces cybersickness due to vestibular-visual conflicts. To mitigate this, this study proposes a hierarchical visual guidance framework. We first introduce a Steering Visual Guidance (SVG) model, which employs a grid-based pattern to provide a stable visual reference frame. While effective, our evaluation revealed that the static, full-field nature of SVG can occlude the user's view and reduce visual clarity. To address this limitation, we optimized the model into Dynamic Steering Visual Guidance (DSVG). Grounded in the physiological principles of central and peripheral vision, DSVG dynamically renders stability cues exclusively within the foveal region, fading them in the periphery based on retinal sensitivity. A user study demonstrates that both SVG and DSVG significantly reduce subjective discomfort and physiological markers of sickness compared to a control condition without cues. Crucially, DSVG achieves sickness mitigation comparable to SVG while reducing visual occlusion by approximately 70%. These findings suggest that DSVG offers a robust, occlusion-minimizing solution for deploying RDW in constrained physical spaces.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}