PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models

doi:10.1109/TVCG.2020.3003823

	PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
	Gao, Lin 4,5; Zhang, Ling-Xiao 4,5; Meng, Hsien-Yu 3; Ren, Yi-Hui 4,5; Lai, Yu-Kun 2; Kobbelt, Leif 1
刊名	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
	2021-06-01
卷号	27 期号:6 页码:3007-3018
关键词	Three-dimensional displays Shape Geometry Two dimensional displays Feature extraction Solid modeling Computational modeling Unsupervised learning convolutional neural network symmetry detection 3D models planar reflective symmetry
ISSN号	1077-2626
DOI	10.1109/TVCG.2020.3003823
英文摘要	In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this article, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces.
资助项目	National Natural Science Foundation of China[61872440] ; National Natural Science Foundation of China[61828204] ; Beijing Municipal Natural Science Foundation[L182016] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Youth Innovation Promotion Association CAS ; CCF-Tencent Open Fund ; Tencent AI Lab Rhino-Bird Focused Research Program[JR202024] ; Open Project Program of the National Laboratory of Pattern Recognition[201900055]
WOS研究方向	Computer Science
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000649620700018
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17680]
专题	中国科学院计算技术研究所
通讯作者	Gao, Lin
作者单位	1.Rhein Westfal TH Aachen, Inst Comp Graph & Multimedia, D-52062 Aachen, Germany 2.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 3AA, Wales 3.Univ Maryland, College Pk, MD 20742 USA 4.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Gao, Lin,Zhang, Ling-Xiao,Meng, Hsien-Yu,et al. PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2021,27(6):3007-3018.
APA	Gao, Lin,Zhang, Ling-Xiao,Meng, Hsien-Yu,Ren, Yi-Hui,Lai, Yu-Kun,&Kobbelt, Leif.(2021).PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,27(6),3007-3018.
MLA	Gao, Lin,et al."PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 27.6(2021):3007-3018.