Variational Autoencoders for Localized Mesh Deformation Component Analysis

doi:10.1109/TPAMI.2021.3085887

	Variational Autoencoders for Localized Mesh Deformation Component Analysis
	Tan, Qingyang 1,2; Zhang, Ling-Xiao 1; Yang, Jie 1,3; Lai, Yu-Kun 4; Gao, Lin 1,3
	2022-10-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	44 期号:10 页码:6297-6310
摘要	Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale nonlinear deformations, and may not always be able to identify important deformation components. In this paper we propose a mesh-based variational autoencoder architecture that is able to cope with meshes with irregular connectivity and nonlinear deformations, assuming that the analyzed dataset contains meshes with the same vertex connectivity, which is common for deformation analysis. To help localize deformations, we introduce sparse regularization in this framework, along with spectral graph convolutional operations. Through modifying the regularization formulation and allowing dynamic change of sparsity ranges, we improve the visual quality and reconstruction ability of the extracted deformation components. Our system also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. As an important application of localized deformation components and a novel approach on its own, we further develop a neural shape editing method, achieving shape editing and deformation component extraction in a unified framework, and ensuring plausibility of the edited shapes. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations. We also demonstrate the effectiveness of our method for neural shape editing.
关键词	Strain Shape Three-dimensional displays Principal component analysis Geometry Convolution Solid modeling 3D meshes variational autoencoder graph convolution sparsity regularization
DOI	10.1109/TPAMI.2021.3085887
收录类别	SCI
语种	英语
资助项目	Newton Advanced Fellowship from the Royal Society[NAFnR2n192151] ; Youth Innovation Promotion Association, CAS[2019108] ; National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[61872440] ; Beijing Municipal Natural Science Foundation[L182016] ; Tencent AI Lab Rhino-Bird Focused Research Program[JR202024]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000853875300034
出版者	IEEE COMPUTER SOC
引用统计	被引频次：4[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/2XEOYT63/19419
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, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100864, Peoples R China 2.Univ Maryland, College Pk, MD 20742 USA 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales
推荐引用方式 GB/T 7714	Tan, Qingyang,Zhang, Ling-Xiao,Yang, Jie,et al. Variational Autoencoders for Localized Mesh Deformation Component Analysis[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2022,44(10):6297-6310.
APA	Tan, Qingyang,Zhang, Ling-Xiao,Yang, Jie,Lai, Yu-Kun,&Gao, Lin.(2022).Variational Autoencoders for Localized Mesh Deformation Component Analysis.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,44(10),6297-6310.
MLA	Tan, Qingyang,et al."Variational Autoencoders for Localized Mesh Deformation Component Analysis".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44.10(2022):6297-6310.