UM  > 科技學院
Unsupervised Learning 3D Local Feature from Raw Voxels based on A Novel Permutation Voxelization Strategy
Zhizhong Han1; Zhenbao Liu1; Junwei Han1; Chi-Man Vong2; Shuhui Bu1; C. L. Philip Chen3
2019-02
Source PublicationIEEE TRANSACTIONS ON CYBERNETIC
ISSN2168-2267
Volume49Issue:2Pages:481 - 494
Abstract

Effective 3-D local features are significant elements for 3-D shape analysis. Existing hand-crafted 3-D local descriptors are effective but usually involve intensive human intervention and prior knowledge, which burdens the subsequent processing procedures. An alternative resorts to the unsupervised learning of features from raw 3-D representations via popular deep learning models. However, this alternative suffers from several significant unresolved issues, such as irregular vertex topology, arbitrary mesh resolution, orientation ambiguity on the 3-D surface, and rigid and slightly nonrigid transformation invariance. To tackle these issues, we propose an unsupervised 3-D local feature learning framework based on a novel permutation voxelization strategy to learn high-level and hierarchical 3-D local features from raw 3-D voxels. Specifically, the proposed strategy first applies a novel voxelization which discretizes each 3-D local region with irregular vertex topology and arbitrary mesh resolution into regular voxels, and then, a novel permutation is applied to permute the voxels to simultaneously eliminate the effect of rotation transformation and orientation ambiguity on the surface. Based on the proposed strategy, the permuted voxels can fully encode the geometry and structure of each local region in regular, sparse, and binary vectors. These voxel vectors are highly suitable for the learning of hierarchical common surface patterns by stacked sparse autoencoder with hierarchical abstraction and sparse constraint. Experiments are conducted on three aspects for evaluating the learned local features: 1) global shape retrieval; 2) partial shape retrieval; and 3) shape correspondence. The experimental results show that the learned local features outperform the other state-of-the-art 3-D shape descriptors.

Keyword3-d Local Features 3-d Voxelization Deep Learning Stacked Sparse Autoencoder (Ssae) Unsupervised Feature Learning
DOIhttp://doi.org/10.1109/TCYB.2017.2778764
Language英语
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS IDWOS:000456733900010
Fulltext Access
Citation statistics
Document TypeJournal article
CollectionFaculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorZhenbao Liu
Affiliation1.Northwestern Polytechnical University, Xi’an 710072, China
2.the Department of Computer and Information Science, University of Macau, Macau 99999, China
3.the Faculty of Science and Technology, University of Macau, Macau 99999, China
Recommended Citation
GB/T 7714
Zhizhong Han,Zhenbao Liu,Junwei Han,et al. Unsupervised Learning 3D Local Feature from Raw Voxels based on A Novel Permutation Voxelization Strategy[J]. IEEE TRANSACTIONS ON CYBERNETIC,2019,49(2):481 - 494.
APA Zhizhong Han,Zhenbao Liu,Junwei Han,Chi-Man Vong,Shuhui Bu,&C. L. Philip Chen.(2019).Unsupervised Learning 3D Local Feature from Raw Voxels based on A Novel Permutation Voxelization Strategy.IEEE TRANSACTIONS ON CYBERNETIC,49(2),481 - 494.
MLA Zhizhong Han,et al."Unsupervised Learning 3D Local Feature from Raw Voxels based on A Novel Permutation Voxelization Strategy".IEEE TRANSACTIONS ON CYBERNETIC 49.2(2019):481 - 494.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhizhong Han]'s Articles
[Zhenbao Liu]'s Articles
[Junwei Han]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhizhong Han]'s Articles
[Zhenbao Liu]'s Articles
[Junwei Han]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhizhong Han]'s Articles
[Zhenbao Liu]'s Articles
[Junwei Han]'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.