Computer Animation and Virtual Worlds最新文献

{"title":"CIG-Diff: Clinical-Intent and Geometry-Aware Diffusion for Low-Light Endoscopic Image Enhancement","authors":"Hong Zou,&nbsp;Wanshu Fan,&nbsp;Zhongbin Han,&nbsp;Dongsheng Zhou","doi":"10.1002/cav.70175","DOIUrl":"https://doi.org/10.1002/cav.70175","url":null,"abstract":"<div>\u0000 \u0000 <p>Low-light image enhancement remains challenging due to the complex coupling between spatially varying illumination and surface reflectance. Existing approaches predominantly emphasize brightness correction or feature-level reconstruction, often leading to color distortion and structural inconsistency under severe illumination degradation. To address these limitations, we propose CIG-Diff, a geometry-aware conditional diffusion framework for structure-constrained low-light enhancement, with endoscopic imaging as a representative application. Instead of treating enhancement as purely photometric correction, CIG-Diff formulates it as a geometry-consistent reconstruction process within a diffusion paradigm. We introduce a cross-modal modulation (CMM) mechanism that incorporates CLIP-encoded textual embeddings as high-level task priors. These embeddings are injected into the diffusion U-Net via conditional modulation to stabilize the denoising trajectory and maintain contextual coherence during restoration. To explicitly model illumination degradation, we further design a geometry-aware illumination module (GAIM) inspired by Retinex theory. GAIM disentangles illumination and reflectance components and performs reflectance recalibration to mitigate spatially non-uniform lighting while preserving geometric consistency and suppressing noise amplification. Extensive experiments demonstrate consistent improvements in quantitative performance and structural fidelity compared with state-of-the-art low-light enhancement methods.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148994605","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":"Efficient Parser-Free Virtual Try-On With Context-Aware Alignment and Edge-Guided Detail Generation","authors":"Jingyun Liu,&nbsp;Han Liu,&nbsp;Shuo Tong","doi":"10.1002/cav.70181","DOIUrl":"https://doi.org/10.1002/cav.70181","url":null,"abstract":"<div>\u0000 \u0000 <p>Virtual try-on (VTON) is an important technique for human-centric garment visualization, digital fashion presentation, and virtual human appearance editing. Existing methods often rely on explicit human representations, such as pose estimation and semantic parsing, which require additional preprocessing, prolong the inference process, and make the synthesis quality sensitive to structural estimation errors. To address these limitations, we propose CAEG-VTON, an efficient parser-free VTON framework with context-aware alignment and edge-guided detail generation. CAEG-VTON adopts a teacher–student paradigm, where ContextEdgeNet uses rich human representations during training to learn garment–body alignment and detail-preserving synthesis, while LiteFitNet inherits such knowledge through distillation and performs inference using only the human image and target garment. LiteFitNet further integrates compact feature extraction, human–garment feature fusion, and an inverted-residual generation structure to efficiently preserve garment shape, boundaries, and texture details. Experiments on VITON and VITON-HD demonstrate that CAEG-VTON improves garment structure, boundary clarity, texture preservation, and distribution-level realism while maintaining a favorable balance between model compactness and inference efficiency. These results show its potential for lightweight virtual garment visualization.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993999","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":"Usage of Virtual User Manuals for Increasing Knowledge About Emergency Procedures: Case Study of North Macedonia and Bosnia and Herzegovina","authors":"Ehlimana Cogo,&nbsp;Emir Cogo,&nbsp;Lina Miloshevska","doi":"10.1002/cav.70180","DOIUrl":"https://doi.org/10.1002/cav.70180","url":null,"abstract":"<div>\u0000 \u0000 <p>Emergency procedures are an important domain for safety education. Modern multimedia technologies aim to aid this process by replacing real-life drills and hazard procedures with virtual simulations. However, there is a limited amount of existing research on this topic, especially focusing on the Western Balkans region. This paper presents a 3D virtual learning environment for emergency procedures in the form of a serious game. The virtual user manual uses the 2D fire evacuation plan of a university building in Ohrid, North Macedonia, for teaching civilians about multiple emergency procedures emergency exits, fire alarms, fire extinguishers, and wall hydrants. A case study was performed on 90 participants from Bosnia and Herzegovina and North Macedonia. Four different scenarios of interest were utilized, general knowledge about emergency procedures, emergency exit simulation, virtual user manual simulation, and emergency procedures involving a cultural heritage site. The achieved results indicate that participants are open to the usage of modern multimedia technologies, that familiarity with the presented location affects the success of learning, and that there is a strong potential for successful usage of virtual user manuals in the region of the Western Balkans in the future.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942604","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":"CapsAR-STEM: Integrating Capsule Networks With Augmented Reality Learning Cards for Enhanced Children's STEM Spatial Cognition in Elementary Education","authors":"Shuyi Zhang,&nbsp;Jian Teng","doi":"10.1002/cav.70179","DOIUrl":"https://doi.org/10.1002/cav.70179","url":null,"abstract":"<div>\u0000 \u0000 <p>Augmented reality (AR) learning cards present a promising medium for fostering spatial cognition in early STEM education, yet prevailing systems rely on conventional convolutional neural networks that discard critical spatial hierarchies during object recognition. This study proposes CapsAR-STEM, a novel framework that integrates Capsule Networks (CapsNet) with marker-based AR learning cards to scaffold elementary children's spatial reasoning and STEM vocabulary acquisition. The CapsNet module preserves part-whole spatial relationships through dynamic routing between capsules, enabling robust recognition of card-bound 3D objects across rotations, scales, and partial occlusions. A pedagogically sequenced AR interaction pipeline renders context-sensitive 3D STEM models and delivers adaptive spatial vocabulary prompts aligned with each child's proficiency profile. Experimental evaluation with 36 parent–child pairs (children aged 6–9 years) demonstrated significant improvements in spatial vocabulary comprehension (<i>p</i> &lt; 0.01, Cohen's <i>d</i> = 0.91) and STEM concept retention (<i>p</i> &lt; 0.01) compared to a conventional AR flashcard baseline. The CapsNet recognition module achieved 92.4% classification accuracy across 68 card categories with notably superior robustness to viewpoint variation (88.7% under 45° rotation) relative to a MobileNetV2 baseline (79.3%). Usability assessments revealed high parental satisfaction (<i>M</i> = 5.3/7.0) and sustained child engagement (<i>M</i> = 4.6/5.0). Because the experimental condition differs from the baseline in both recognition architecture and adaptive scaffolding, the present study evaluates CapsAR-STEM as an integrated system; the monotonic relationship between capsule-relevant vocabulary dimensions and learning gains is interpreted as suggestive, rather than definitive, mechanistic evidence, and a recognition-only ablation is identified as necessary future work. Results indicate that capsule-based spatial hierarchy preservation, combined with pedagogically grounded AR interaction design, provides effective scaffolding for children's STEM spatial cognition development.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148811256","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":"Topology-Aware AR With \u0000 \u0000 \u0000 \u0000 \u0000 G\u0000 \u0000 \u0000 3\u0000 \u0000 \u0000 \u0000 $$ {G}^3 $$\u0000 -\u0000 \u0000 \u0000 D\u0000 e\u0000 p\u0000 t\u0000 h\u0000 \u0000 $$ Depth $$\u0000 for Minimally Invasive Surgery","authors":"Qinghong Gao,&nbsp;Wen Tang,&nbsp;TaoRuan Wan","doi":"10.1002/cav.70171","DOIUrl":"https://doi.org/10.1002/cav.70171","url":null,"abstract":"<div>\u0000 \u0000 <p>This study proposes a topology-aware 3D augmented reality (AR) framework for minimally invasive surgery (MIS) and robot-assisted MIS (RAMIS) to address the limited field of view and lack of depth perception in 2D endoscopic imaging. Central to the framework is a novel self-supervised depth estimation method, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mrow>\u0000 <mi>G</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>3</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ {G}^3 $$</annotation>\u0000 </semantics></math>-<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>D</mi>\u0000 <mi>e</mi>\u0000 <mi>p</mi>\u0000 <mi>t</mi>\u0000 <mi>h</mi>\u0000 </mrow>\u0000 <annotation>$$ Depth $$</annotation>\u0000 </semantics></math>, which employs a translation-to-permutation encoder with group equivariance and four-connectivity graph structures to capture non-Euclidean geometric features and generate accurate 3D point clouds, particularly for surgical instruments. The reconstructed depth maps enable real-time AR overlays, Poisson surface-based mesh reconstruction, and precise instrument–organ distance measurement. Extensive evaluation on DaVinci, SCARED, SERV-CT, and Hamlyn heart datasets demonstrates significant performance improvements over state-of-the-art methods, with Abs Rel gains of approximately <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>39</mn>\u0000 <mo>.</mo>\u0000 <mn>4</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 39.4% $$</annotation>\u0000 </semantics></math> and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>32</mn>\u0000 <mo>.</mo>\u0000 <mn>6</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 32.6% $$</annotation>\u0000 </semantics></math>. Validation in multiple surgical scenarios confirms enhanced depth perception and reliable spatial awareness, highlighting the framework's potential to improve surgical precision, safety, and clinical outcomes.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148811257","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":"Artificial Intelligence for Adaptive Virtual Reality: Methods, Applications, and Future Prospects","authors":"Barkha Kanjwani,&nbsp;Ahmed Ewais,&nbsp;Fisnik Dalipi,&nbsp;Sher Muhammad Daudpota,&nbsp;Zenun Kastrati,&nbsp;Ali Shariq Imran","doi":"10.1002/cav.70158","DOIUrl":"https://doi.org/10.1002/cav.70158","url":null,"abstract":"<div>\u0000 \u0000 <p>Virtual Reality (VR) is a transformative technology offering immersive and interactive experiences, revolutionizing fields. However, VR cannot be applied as a one-size-fits-all solution for diverse users, creating a major challenge that demands adaptive and personalized approaches. Artificial Intelligence (AI) has become a crucial enabler of such personalization, yet the specific ways in which AI techniques are implemented to create adaptive VR systems remain insufficiently synthesized in the current literature. This study addresses this gap by presenting a comprehensive overview and analysis of existing AI-driven methods and approaches used to deliver adaptive VR applications. A review of 33 high-quality studies reveals that AI, including classical Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), Reinforcement Learning (RL), Computer Vision (CV), and Large Language Models (LLMs), forms the backbone of VR's evolution toward more user-centric experiences. Current research is dominated by applications in entertainment, education, and healthcare, while manufacturing, engineering, and cultural heritage are also advancing. AI enhances VR through real-time 3D content generation, intelligent avatars, gesture recognition, and immersive feedback. Nevertheless, challenges such as computational demands, latency, limited generalizability, and ethical concerns about data privacy and transparency persist, highlighting directions for future research.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783903","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":"HoloDiff: Holistic Talking Human Animation Via Latent Diffusion","authors":"Xinmu Wang,&nbsp;Fumi Honda,&nbsp;Xiang Gao,&nbsp;Junqi Huang,&nbsp;Wei Chen,&nbsp;Xianfeng David Gu","doi":"10.1002/cav.70173","DOIUrl":"https://doi.org/10.1002/cav.70173","url":null,"abstract":"<div>\u0000 \u0000 <p>Holistic talking human animation aims to synthesize coordinated facial expressions and body poses that are consistent with spoken content and human communication patterns. This task requires both realistic motion generation and accurate temporal alignment between speech and motion, which remain challenging for existing methods that model facial and bodily motion separately or operate in high-dimensional motion spaces. We present HoloDiff, a latent diffusion framework for holistic talking human animation. Given an input speech signal, HoloDiff encodes facial and bodily dynamics into a compact and structured latent representation that preserves anatomical structure and cross-part interactions. A speech-conditioned diffusion process is then applied in this latent space to model long-range temporal dynamics and generate motion sequences aligned with audio input. By performing diffusion in a structured latent space, HoloDiff reduces modeling complexity while improving temporal coherence and audio–motion alignment. Extensive experiments on the SHOW dataset demonstrate that HoloDiff produces more realistic and expressive talking human animation and achieves better multimodal correspondence between speech and motion compared to baselines.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752581","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":"Keyframe-Guided Self-Supervised Learning Framework for Physics-Based Garment Animation","authors":"Peng Zhang,&nbsp;Xu Cao,&nbsp;Bo Fei,&nbsp;Jie Zhang","doi":"10.1002/cav.70168","DOIUrl":"https://doi.org/10.1002/cav.70168","url":null,"abstract":"<div>\u0000 \u0000 <p>Generating realistic and controllable 3D garment animations across multiple clothing categories under limited supervision remains a fundamental challenge in virtual clothing design and animation. To tackle this, we propose a physics-aware, keyframe-guided self-supervised framework for multi-category garment animation. First, a graph neural network (GNN) is employed to extract structural features from both human skeletal motion sequences and garment templates, and dynamically associate them to capture non-rigid deformations in response to human motion. A physics-constrained transformer module is then introduced to enforce physical plausibility through a multi-objective loss that includes elasticity, bending, collision, and inertial consistency terms. Furthermore, we design a latent-space-based decoupling mechanism to encode garment simulation parameters, enabling fine-grained parameter control by mapping keyframes to simulation attributes via radial basis function (RBF) interpolation. Lastly, an interpolated attention-based sequence calibration module is proposed to inject keyframe-guided topology features into the decoding process, enhancing the temporal continuity and topological consistency of the generated garment sequences. Experimental results demonstrate that our method produces physically realistic, dynamically stable, and highly detailed garment animations even under weak supervision, with strong generalization capabilities across diverse garment types.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752582","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":"Visualization and Evaluation of Biological Network Applications in Virtual Reality Environments","authors":"Musaab Osamah Anwer,&nbsp;Ezzeddine Zagrouba","doi":"10.1002/cav.70170","DOIUrl":"https://doi.org/10.1002/cav.70170","url":null,"abstract":"<div>\u0000 \u0000 <p>The lack of standardized evaluation frameworks for virtual reality applications in specialized fields makes it difficult to assess quality and compare various systems. This research develops a comprehensive evaluation framework for immersive VR applications, with a focus on biological data visualization systems. The framework integrates standard software engineering metrics with domain-specific VR measurement tools. It provides measurable indicators for immersion depth and interaction accuracy, addressing current challenges in VR assessment methods. The approach was validated through a VR application designed for biological network visualization, which enables researchers to explore gene-disease links using real data from the National Center for Biotechnology Information. The evaluation involved 20 biology experts specializing in molecular biology, genetics, bioinformatics, and cell biology. Results demonstrated excellent performance across all metrics, with a 99.29% task success rate, an 86.375 System Usability Scale score, a 4.61 out of 5 immersion rating, and 98.2% interaction accuracy across seven types of VR interactions. The framework offers essential objective measures for VR-specific features while remaining compatible with established usability metrics. It addresses the need for standardized VR evaluation methods by providing practical tools for assessing immersive scientific applications. It sets VR evaluation standards for scientific visualization and provides a validated, reusable framework.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752547","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":"Enhancing Product Ideation Workflows Through Immersive Interaction: A Task-Centered Study in Virtual Reality","authors":"Bowen Lai,&nbsp;Meng Wan","doi":"10.1002/cav.70177","DOIUrl":"https://doi.org/10.1002/cav.70177","url":null,"abstract":"<div>\u0000 \u0000 <p>Virtual Reality (VR) has gained significant momentum in creative endeavors due to its unique characteristics of immersion, interaction, and imagination. However, effectively harnessing its “imagination” potential—specifically how VR content influences creative ability and empowers humans in goal-oriented tasks like product design—remains a challenge. This paper presents a tailored Immersive Ideation System (IIS) for product appearance design. The system enables designers to perform sketching, modeling, and conceptual review within integrated VR scenes, fostering a fluid and seamless ideation workflow. To evaluate the efficacy of the IIS, we conducted a comprehensive task-centered user study involving 24 industrial design students and 6 professional designers. Our analysis focuses on the influence of VR environments on creative behaviors and design outputs. The results suggest that while specific VR conditions relate to differences in design flexibility and originality, they also introduce potential trade-offs with design fixation, offering tentative insights for the configuration of future immersive design workspaces.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148647722","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}