Learning on 3D Meshes With Laplacian Encoding and Pooling

doi:10.1109/TVCG.2020.3014449

	Learning on 3D Meshes With Laplacian Encoding and Pooling
	Qiao, Yi-Ling 1,2; Gao, Lin 1,3; Yang, Jie 1,3; Rosin, Paul L.4; Lai, Yu-Kun 4; Chen, Xilin 3,5
	2022-02-01
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
ISSN	1077-2626
卷号	28 期号:2 页码:1317-1327
摘要	3D models are commonly used in computer vision and graphics. With the wider availability of mesh data, an efficient and intrinsic deep learning approach to processing 3D meshes is in great need. Unlike images, 3D meshes have irregular connectivity, requiring careful design to capture relations in the data. To utilize the topology information while staying robust under different triangulations, we propose to encode mesh connectivity using Laplacian spectral analysis, along with mesh feature aggregation blocks (MFABs) that can split the surface domain into local pooling patches and aggregate global information amongst them. We build a mesh hierarchy from fine to coarse using Laplacian spectral clustering, which is flexible under isometric transformations. Inside the MFABs there are pooling layers to collect local information and multi-layer perceptrons to compute vertex features of increasing complexity. To obtain the relationships among different clusters, we introduce a Correlation Net to compute a correlation matrix, which can aggregate the features globally by matrix multiplication with cluster features. Our network architecture is flexible enough to be used on meshes with different numbers of vertices. We conduct several experiments including shape segmentation and classification, and our method outperforms state-of-the-art algorithms for these tasks on the ShapeNet and COSEG datasets.
关键词	Three-dimensional displays Laplace equations Shape Correlation Machine learning Topology Computational modeling Mesh processing segmentation laplacian deep learning
DOI	10.1109/TVCG.2020.3014449
收录类别	SCI
语种	英语
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[NAFnR2n192151] ; Youth Innovation Promotion Association CAS ; CCF-Tencent Open Fund ; Open Project Program of the National Laboratory of Pattern Recognition[201900055]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000736740300009
出版者	IEEE COMPUTER SOC
引用统计	被引频次：14[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/2XEOYT63/18317
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, Dept Comp Sci, 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 5.Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Qiao, Yi-Ling,Gao, Lin,Yang, Jie,et al. Learning on 3D Meshes With Laplacian Encoding and Pooling[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2022,28(2):1317-1327.
APA	Qiao, Yi-Ling,Gao, Lin,Yang, Jie,Rosin, Paul L.,Lai, Yu-Kun,&Chen, Xilin.(2022).Learning on 3D Meshes With Laplacian Encoding and Pooling.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,28(2),1317-1327.
MLA	Qiao, Yi-Ling,et al."Learning on 3D Meshes With Laplacian Encoding and Pooling".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 28.2(2022):1317-1327.