中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles

文献类型：期刊论文

作者Shi, Min3; Zhuo, Xinru3; Li, Zhenyu3; Sun, Yueyue3; Gao, Lin1; Mao, Tianlu1; Zhu, Dengming1; Yang, Yongliang2
刊名COMPUTER ANIMATION AND VIRTUAL WORLDS
出版日期2025-11-19
卷号36期号:6页码:15
关键词garment animation neural networks physical simulation
ISSN号1546-4261
DOI10.1002/cav.70076
英文摘要Dressing animations have broad applications in film and animation, but current methods require retraining networks for new styles, which is resource-intensive. While 2D pattern parameters are used for static 3D clothing modeling and editing, applying them to control style variations in dynamic clothing deformation is challenging due to the uncertainty introduced by multiple parameters. Ensuring consistent and stable style features across time-varying deformation sequences is difficult. Therefore, we present StyleGarNet, a novel approach for style-parameter-controlled dressing animation generation and editing. We employ a conditional variational autoencoder architecture to build our network, with style parameters serving as constraint information. This allows us to learn the probabilistic distribution model of deformations under style constraints, crucial for enhancing the robust representation of styles during the deformation process. Simultaneously, considering the temporal nature of motion, we introduce a transformer layer to capture the temporal dependencies of both motion and clothing deformation, thereby enhancing the stability of clothing deformation. Ultimately, our approach enables flexible manipulation of dressing animation generation through inputting style and motion features. Evaluation results demonstrate the efficacy of our approach and show that StyleGarNet outperforms existing methods in terms of prediction speed, accuracy, and stability of deformation sequences.
资助项目National Natural Science Foundation of China[61972379]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001617846200001
出版者WILEY
源URL[http://119.78.100.204/handle/2XEOYT63/43063]  
专题中国科学院计算技术研究所
通讯作者Zhu, Dengming
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
2.Univ Bath, Dept Comp Sci, Bath, England
3.North China Elect Power Univ, Sch Control & Comp Engn, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Shi, Min,Zhuo, Xinru,Li, Zhenyu,et al. StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles[J]. COMPUTER ANIMATION AND VIRTUAL WORLDS,2025,36(6):15.
APA Shi, Min.,Zhuo, Xinru.,Li, Zhenyu.,Sun, Yueyue.,Gao, Lin.,...&Yang, Yongliang.(2025).StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles.COMPUTER ANIMATION AND VIRTUAL WORLDS,36(6),15.
MLA Shi, Min,et al."StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles".COMPUTER ANIMATION AND VIRTUAL WORLDS 36.6(2025):15.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。