File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Unsupervised Learning of Intrinsic Structural Representation Points

TitleUnsupervised Learning of Intrinsic Structural Representation Points
Authors
KeywordsThree-dimensional displays
Feature extraction
Semantics
Principal component analysis
Machine learning
Issue Date2020
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147
Citation
Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 13-19 June 2020, v. 1, p. 9118-9127 How to Cite?
AbstractLearning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points produced by our method encode the shape structure intrinsically and exhibit semantic consistency across all the shape instances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves comparable performance with the state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints.
Persistent Identifierhttp://hdl.handle.net/10722/294313
ISSN

 

DC FieldValueLanguage
dc.contributor.authorCHEN, N-
dc.contributor.authorLiu, L-
dc.contributor.authorCUI, Z-
dc.contributor.authorCHEN, R-
dc.contributor.authorCeylan, D-
dc.contributor.authorTu, C-
dc.contributor.authorWang, WP-
dc.date.accessioned2020-11-23T08:29:35Z-
dc.date.available2020-11-23T08:29:35Z-
dc.date.issued2020-
dc.identifier.citationProceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 13-19 June 2020, v. 1, p. 9118-9127-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/294313-
dc.description.abstractLearning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points produced by our method encode the shape structure intrinsically and exhibit semantic consistency across all the shape instances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves comparable performance with the state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints.-
dc.languageeng-
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147-
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognition. Proceedings-
dc.rightsIEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright © IEEE Computer Society.-
dc.rights©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectThree-dimensional displays-
dc.subjectFeature extraction-
dc.subjectSemantics-
dc.subjectPrincipal component analysis-
dc.subjectMachine learning-
dc.titleUnsupervised Learning of Intrinsic Structural Representation Points-
dc.typeConference_Paper-
dc.identifier.emailWang, WP: wenping@cs.hku.hk-
dc.identifier.authorityWang, WP=rp00186-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR42600.2020.00914-
dc.identifier.hkuros319173-
dc.identifier.volume1-
dc.identifier.spage9118-
dc.identifier.epage9127-
dc.publisher.placeUnited States-
dc.identifier.issnl1063-6919-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats