Journal of Computer Science and Technology


Motion-inspired Real-time Garment Synthesis with Temporal-consistency

Yu-Kun Wei1(魏育坤), Member, CCF, Min Shi1,*(石敏), Member, CCF, Wen-Ke Feng1(冯文科), Member, CCF, Deng-Ming Zhu2(朱登明), Member, CCF, Tian-Lu Mao2(毛天露), Member, CCF   

  1. 1School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
    2Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Published:2022-09-07
  • Contact: Min Shi
  • About author:Min Shi is an associate professor in the school of Control and Computer Engineering, North China Electric Power University, Beijing. She received her Ph.D. degree in computer science and technology from Chinese Academy of Sciences, Beijing, in 2013. Her research interests include cloth simulation, computer vision and virtual reality.

Synthesizing garment dynamics according to body motion is a vital technique in computer graphics. Physics-based simulation depends on an accurate model of the law of kinetics of cloth, which is time-consuming, hard to implement, and complex to control. Existing data-driven approaches either lack temporal consistency, or fail to handle garments that are different from body topology. In this paper, we present a motion-inspired real-time garment synthesis workflow that enables high-level control of garment shape. Given a sequence of body motions, our workflow is able to generate corresponding garment dynamics with both spatial and temporal coherence. To that end, we develop a Transformer-based garment synthesis network to learn the mapping from body motion to garment dynamics. Frame-level attention is employed to capture the dependency of garment and body motion. Moreover, a post-processing procedure is further taken to perform penetration removal and auto-texturing. Then, textured clothing animation that is collision-free and temporally-consistent is generated. We quantitatively and qualitatively evaluated our proposed workflow from different aspects. Extensive experiments demonstrate that our network is able to deliver clothing dynamics which retain the wrinkles from physics-based simulation it is learned from, while running 1000 times faster. Besides, our workflow achieved superior synthesis performance compared with alternative approaches. To stimulate further research in this direction, our code will be publicly available soon. 



Key words: clothing animation; computer graphics; transformer; temporal consistency;

[1] Hua-Peng Wei, Ying-Ying Deng, Fan Tang, Xing-Jia Pan, and Wei-Ming Dong. A Comparative Study of CNN- and Transformer-Based Visual Style Transfer [J]. Journal of Computer Science and Technology, 2022, 37(3): 601-614.
[2] Ze-Lin Zhao, Di Huang, and Xiao-Xing Ma. TOAST: Automated Testing of Object Transformers in Dynamic Software Updates [J]. Journal of Computer Science and Technology, 2022, 37(1): 50-66.
[3] Bo Ren, Xu-Yun Yang, Ming C. Lin, Nils Thuerey, Matthias Teschner, Chenfeng Li. Visual Simulation of Multiple Fluids in Computer Graphics: A State-of-the-Art Report [J]. , 2018, 33(3): 431-451.
[4] Xu-Ran Zhao, Xun Wang, Qi-Chao Chen. Temporally Consistent Depth Map Prediction Using Deep CNN and Spatial-temporal Conditional Random Field [J]. , 2017, 32(3): 443-456.
[5] Ming-Ming Cheng, Qi-Bin Hou, Song-Hai Zhang, Paul L. Rosin. Intelligent Visual Media Processing: When Graphics Meets Vision [J]. , 2017, 32(1): 110-121.
[6] Bai-Lin Yang, Frederick W. B. Li, Zhi-Geng Pan, and Xun Wang. An Effective Error Resilient Packetization Scheme for Progressive Mesh Transmission over Unreliable Networks [J]. , 2008, 23(6 ): 1015-1025 .
[7] Yong-Wei Miao, Jie-Qing Feng, Chun-Xia Xiao, Qun-Sheng Peng and A.R. Forrest. Differentials-based segmentation and parameterization for point-sampled surfaces [J]. , 2007, 22(5): 749-760 .
[8] Feng Xue, You-Sheng Zhang, Ju-Lang Jiang, Min Hu, Xin-Dong Wu, and Rong-Gui Wang. Real-Time Texture Synthesis Using s-Tile Set [J]. , 2007, 22(4): 590-596 .
[9] Xue-Ying Qin, Eihachiro Nakamae, Wei Hua, Yasuo Nagai, and Qun-Sheng Peng. Anti-Aliased Rendering of Water Surface [J]. , 2004, 19(5): 0-0.
[10] Fu-Li Wu, Chun-Hui Mei, and Jiao-Ying Shi. Method of Direct Texture Synthesis on Arbitrary Surfaces [J]. , 2004, 19(5): 0-0.
[11] A. R. Forrest. Future Trends in Computer Graphics: How Much is Enough? [J]. , 2003, 18(5): 0-0.
[12] Liang Xundong; Li Bin; Liu Shenquan;. Three-Dimensional Vector Field Visualization Based on Tensor Decomposition [J]. , 1996, 11(5): 452-460.
[13] Qin Kaihuai; Gong Minglun; Tong Geliang;. Fast Ray Tracing NURBS Surfaces [J]. , 1996, 11(1): 17-29.
Full text



No Suggested Reading articles found!

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
  Copyright ©2015 JCST, All Rights Reserved