Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders

doi:10.1109/TVCG.2021.3112526

	Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders
	Yang, Jie 1,2; Gao, Lin 1,2; Tan, Qingyang 3; Huang, Yi-Hua 1,2; Xia, Shihong 1,2; Lai, Yu-Kun 4
	2023-02-01
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
ISSN	1077-2626
卷号	29 期号:2 页码:1301-1317
摘要	Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this article, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.
关键词	Multi-scale shape analysis attention mechanism sparse regularization stacked auto-encoder
DOI	10.1109/TVCG.2021.3112526
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[61872440] ; Beijing Municipal Natural Science Foundation[L182016] ; Science and Technology Service Network Initiative ; Chinese Academy of Sciences[KFJ-STS-QYZD-2021-11-001] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Youth Innovation Promotion Association CAS ; Zhejiang Lab[2021KE0AB06]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000906475100002
出版者	IEEE COMPUTER SOC
引用统计	被引频次：7[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/2XEOYT63/20066
专题	中国科学院计算技术研究所期刊论文
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100864, Peoples R China 3.Univ Maryland, College Pk, MD 20742 USA 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales
推荐引用方式 GB/T 7714	Yang, Jie,Gao, Lin,Tan, Qingyang,et al. Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2023,29(2):1301-1317.
APA	Yang, Jie,Gao, Lin,Tan, Qingyang,Huang, Yi-Hua,Xia, Shihong,&Lai, Yu-Kun.(2023).Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,29(2),1301-1317.
MLA	Yang, Jie,et al."Multiscale Mesh Deformation Component Analysis With Attention-Based Autoencoders".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 29.2(2023):1301-1317.