Unsupervised Learning of 3-D Local Features From Raw Voxels Based on a Novel Permutation Voxelization Strategy

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on cybernetics Jg. 49; H. 2; S. 481 - 494
Hauptverfasser: Han, Zhizhong, Liu, Zhenbao, Han, Junwei, Vong, Chi-Man, Bu, Shuhui, Chen, C. L. Philip
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.02.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
3-D local features
3-D voxelization
Ambiguity
deep learning
Feature extraction
Finite element method
Geometry
Machine learning
Permutations
Retrieval
Shape
Shape recognition
Solid modeling
stacked sparse autoencoder (SSAE)
State of the art
Strategy
Three dimensional models
Topology
Transformations
unsupervised feature learning
Unsupervised learning
Visualization
ISSN:2168-2267, 2168-2275, 2168-2275
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2168-2267
2168-2275
2168-2275
DOI:10.1109/TCYB.2017.2778764