StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles

doi:10.1002/cav.70076

CSpace

	StyleGarNet: A Real-Time Garment Animation Generation Method With Diverse Styles
	Shi, Min 1; Zhuo, Xinru 1; Li, Zhenyu 1; Sun, Yueyue 1; Gao, Lin 2; Mao, Tianlu 2; Zhu, Dengming 2; Yang, Yongliang 3
	2025-11-19
发表期刊	COMPUTER ANIMATION AND VIRTUAL WORLDS
ISSN	1546-4261
卷号	36 期号:6 页码:15
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.
关键词	garment animation neural networks physical simulation
DOI	10.1002/cav.70076
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001617846200001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/43064
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.North China Elect Power Univ, Sch Control & Comp Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Univ Bath, Dept Comp Sci, Bath, England
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.