中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Learning-Based Intrinsic Reflectional Symmetry Detection

文献类型：期刊论文

作者Qiao, Yi-Ling4,6; Gao, Lin1,4; Liu, Shu-Zhi1,4; Liu, Ligang5; Lai, Yu-Kun3; Chen, Xilin2
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2023-09-01
卷号29期号:9页码:3799-3808
关键词Mesh processing symmetry detection deep learning intrinsic reflectional symmetry laplacian eigenanalysis
ISSN号1077-2626
DOI10.1109/TVCG.2022.3172361
英文摘要Reflectional symmetry is a ubiquitous pattern in nature. Previous works usually solve this problem by voting or sampling, suffering from high computational cost and randomness. In this article, we propose a learning-based approach to intrinsic reflectional symmetry detection. Instead of directly finding symmetric point pairs, we parametrize this self-isometry using a functional map matrix, which can be easily computed given the signs of Laplacian eigenfunctions under the symmetric mapping. Therefore, we manually label the eigenfunction signs for a variety of shapes and train a novel neural network to predict the sign of each eigenfunction under symmetry. Our network aims at learning the global property of functions and consequently converts the problem defined on the manifold to the functional domain. By disentangling the prediction of the matrix into separated bases, our method generalizes well to new shapes and is invariant under perturbation of eigenfunctions. Through extensive experiments, we demonstrate the robustness of our method in challenging cases, including different topology and incomplete shapes with holes. By avoiding random sampling, our learning-based algorithm is over 20 times faster than state-of-the-art methods, and meanwhile, is more robust, achieving higher correspondence accuracy in commonly used metrics.
资助项目Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[61872440] ; Royal Society Newton Advanced Fellowship[NAF-R2-192151] ; Youth Innovation Promotion Association CAS
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001041912300006
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/21375]  
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; Chen, Xilin
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 101408, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 101408, Peoples R China
3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales
4.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
5.Univ Sci & Technol China, Sch Math Sci, Hefei 230026, Peoples R China
6.Univ Maryland, College Pk, MD 20742 USA
推荐引用方式
GB/T 7714		 Qiao, Yi-Ling,Gao, Lin,Liu, Shu-Zhi,et al. Learning-Based Intrinsic Reflectional Symmetry Detection[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2023,29(9):3799-3808.
APA Qiao, Yi-Ling,Gao, Lin,Liu, Shu-Zhi,Liu, Ligang,Lai, Yu-Kun,&Chen, Xilin.(2023).Learning-Based Intrinsic Reflectional Symmetry Detection.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,29(9),3799-3808.
MLA Qiao, Yi-Ling,et al."Learning-Based Intrinsic Reflectional Symmetry Detection".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 29.9(2023):3799-3808.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。