Computer Animation and Social Agents

The LNCS 15915 constitutes the proceedings from the 38th International Conference on Computer Animation and Social Agents, CASA 2025, held in Strasbourg, France, during June 24, 2025.

The 20 papers (17 from the main conference and 3 from the AniNex workshop) presented were carefully reviewed and selected from 82 submissions. These papers focus on various aspects of Computer Animation and Social Agents, such as Motion Capture & Retargeting, Physics-based Animation, Vision-based Techniques, Behavioral Animation, Facial Animation, Image-based Animation, Virtual Humans, Crowd Simulation, AI-based Animation, Deep Learning Methods, Virtual Humans and Avatars, and 3D Physiological Humans.

Inhalt

.- Speech-Driven 3D Facial Animation with Regional Attention for Style Capture.

.- Perspective Matters: Investigating the Effects of Vibrotactile Mode Design on User Experience in Action-Role Playing Game and Media.

.- Exploring Cultural Heritage with AR: The TAM Case Study of Nvshu.

.- Motion Style Transfer: Methods, Challenges, and Future Directions.

.- ReDACT: Reconstructing Detailed Avatar with Controllable Texture.

.- ShadowCraft-NeRF: Occlusion and Shadow Mitigation via SAM-Guided NeRF.

.- Hybrid-Granularity Image-Music Retrieval Using Contrastive Learning between Images and Music.

.- Text-driven Tree Modeling via CLIP-based Optimization.

.- Virtual Guides and Crowd Behaviors: Understanding Evacuation Decision-Making in Virtual Reality.

.- Visualizing the Invisible: An Efficient Framework for Microscopic Visualization.

.- A Design Study on Contextual and Interactive Serious Games for Children's Learning of Chinese Character Culture.

.- Potential Representation Learning for Visible-Infrared Person Re-Identification in Virtual Surveillance Systems.

.- Improving Fidelity of Close Social Interaction Animations in Social VR with a Machine Learning-based Refinement Framework.

.- Simulation of Ball Levitation with SPH.

.- Summon Arcane: An AI-Driven Pixel Art Game with Interactive Narrative and Immersive Summoning Experience.

.- STA-TAD: Spatial-Temporal Adapter on ViT for Temporal Action Detection.

.- User Interface for Controlling Crowd in Metaverse Using Spatial Controller.

.- Immersion Discrepancies in Educational Serious Games Among Children's Age Groups.

.- Unsupervised Salient Object Detection with Pseudo-Labels Refinement.

.- Intelligent Compilation System for Chinese Character Animation Based on Dynamic Data Sets.