UM  > 科技學院  > 電腦及資訊科學系
Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features with Structure Preservation on 3-D Meshes
Han Z.2; Liu Z.2; Han J.2; Vong C.-M.1; Bu S.2; Chen C.L.P.1
2017-10-01
Source PublicationIEEE Transactions on Neural Networks and Learning Systems
ISSN21622388 2162237X
Volume28Issue:10Pages:2268-2281
Abstract

Discriminative features of 3-D meshes are significant to many 3-D shape analysis tasks. However, handcrafted descriptors and traditional unsupervised 3-D feature learning methods suffer from several significant weaknesses: 1) the extensive human intervention is involved; 2) the local and global structure information of 3-D meshes cannot be preserved, which is in fact an important source of discriminability; 3) the irregular vertex topology and arbitrary resolution of 3-D meshes do not allow the direct application of the popular deep learning models; 4) the orientation is ambiguous on the mesh surface; and 5) the effect of rigid and nonrigid transformations on 3-D meshes cannot be eliminated. As a remedy, we propose a deep learning model with a novel irregular model structure, called mesh convolutional restricted Boltzmann machines (MCRBMs). MCRBM aims to simultaneously learn structure-preserving local and global features from a novel raw representation, local function energy distribution. In addition, multiple MCRBMs can be stacked into a deeper model, called mesh convolutional deep belief networks (MCDBNs). MCDBN employs a novel local structure preserving convolution (LSPC) strategy to convolve the geometry and the local structure learned by the lower MCRBM to the upper MCRBM. LSPC facilitates resolving the challenging issue of the orientation ambiguity on the mesh surface in MCDBN. Experiments using the proposed MCRBM and MCDBN were conducted on three common aspects: Global shape retrieval, partial shape retrieval, and shape correspondence. Results show that the features learned by the proposed methods outperform the other state-of-the-art 3-D shape features.

Keyword3-d Mesh Laplace-beltrami Operator Mesh Convolutional Deep Belief Networks (Mcdbns) Mesh Convolutional Restricted Boltzmann Machines (Mcrbms)
DOI10.1109/TNNLS.2016.2582532
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000411293200005
Fulltext Access
Citation statistics
Cited Times [WOS]:16   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Universidade de Macau
2.Northwestern Polytechnical University
Recommended Citation
GB/T 7714
Han Z.,Liu Z.,Han J.,et al. Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features with Structure Preservation on 3-D Meshes[J]. IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2268-2281.
APA Han Z.,Liu Z.,Han J.,Vong C.-M.,Bu S.,&Chen C.L.P..(2017).Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features with Structure Preservation on 3-D Meshes.IEEE Transactions on Neural Networks and Learning Systems,28(10),2268-2281.
MLA Han Z.,et al."Mesh Convolutional Restricted Boltzmann Machines for Unsupervised Learning of Features with Structure Preservation on 3-D Meshes".IEEE Transactions on Neural Networks and Learning Systems 28.10(2017):2268-2281.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Han J.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Han J.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Han Z.]'s Articles
[Liu Z.]'s Articles
[Han J.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.