Synthesizing Mesh Deformation Sequences With Bidirectional LSTM

doi:10.1109/TVCG.2020.3028961

	Synthesizing Mesh Deformation Sequences With Bidirectional LSTM
	Qiao, Yi-Ling 1,2; Lai, Yu-Kun 4; Fu, Hongbo 5; Gao, Lin 1,3
	2022-04-01
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
ISSN	1077-2626
卷号	28 期号:4 页码:1906-1916
摘要	Synthesizing realistic 3D mesh deformation sequences is a challenging but important task in computer animation. To achieve this, researchers have long been focusing on shape analysis to develop new interpolation and extrapolation techniques. However, such techniques have limited learning capabilities and therefore often produce unrealistic deformation. Although there are already networks defined on individual meshes, deep architectures that operate directly on mesh sequences with temporal information remain unexplored due to the following major barriers: irregular mesh connectivity, rich temporal information, and varied deformation. To address these issues, we utilize convolutional neural networks defined on triangular meshes along with a shape deformation representation to extract useful features, followed by long short-term memory (LSTM) that iteratively processes the features. To fully respect the bidirectional nature of actions, we propose a new share-weight bidirectional scheme to better synthesize deformations. An extensive evaluation shows that our approach outperforms existing methods in sequence generation, both qualitatively and quantitatively.
关键词	Strain Shape Three-dimensional displays Animation Feature extraction Machine learning Computer architecture Mesh deformation mesh sequences LSTM deep learning shape generation
DOI	10.1109/TVCG.2020.3028961
收录类别	SCI
语种	英语
资助项目	Beijing Program for International S&T Cooperation Project[Z191100001619003] ; Beijing Municipal Natural Science Foundation[L182016] ; National Natural Science Foundation of China[61872440] ; National Natural Science Foundation of China[61828204] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Youth Innovation Promotion Association CAS ; Tencent AI Lab Rhino-Bird Focused Research Program[JR202024]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000761227900015
出版者	IEEE COMPUTER SOC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18963
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100864, Peoples R China 2.Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA 3.Univ Chinese Acad Sci, Beijing 100864, Peoples R China 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 3AA, Wales 5.City Univ Hong Kong, Sch Creat Media, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Qiao, Yi-Ling,Lai, Yu-Kun,Fu, Hongbo,et al. Synthesizing Mesh Deformation Sequences With Bidirectional LSTM[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2022,28(4):1906-1916.
APA	Qiao, Yi-Ling,Lai, Yu-Kun,Fu, Hongbo,&Gao, Lin.(2022).Synthesizing Mesh Deformation Sequences With Bidirectional LSTM.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,28(4),1906-1916.
MLA	Qiao, Yi-Ling,et al."Synthesizing Mesh Deformation Sequences With Bidirectional LSTM".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 28.4(2022):1906-1916.