File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: P2MAT-NET: Learning medial axis transform from sparse point clouds

TitleP2MAT-NET: Learning medial axis transform from sparse point clouds
Authors
KeywordsMedial axis transform
Neural networks
Point clouds
Issue Date2020
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/cagd
Citation
Computer Aided Geometric Design, 2020, v. 80, p. article no. 101874 How to Cite?
AbstractThe medial axis transform (MAT) of a 3D shape includes the set of centers and radii of the maximally inscribed spheres, and is a complete shape descriptor that can be used to reconstruct the original shape. It is a compact representation that jointly describes geometry, topology, and symmetry properties of a given shape. In this work, we present P2MAT-NET, a neural network which learns the pattern of sparse point clouds and transform them into spheres approximating MAT. The experimental results illustrate that P2MAT-NET demonstrates better performance than state-of-the-art methods in computing MAT from point clouds, in terms of MAT quality to approximate the 3D shapes. The computed MAT can be used as an intermediate descriptor for downstream applications such as 3D shape recognition from point clouds. Our results show that it can achieve competitive performance in recognition with state-of-the-art methods.
Persistent Identifierhttp://hdl.handle.net/10722/293779
ISSN
2023 Impact Factor: 1.3
2023 SCImago Journal Rankings: 0.602
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYang, B-
dc.contributor.authorYao, J-
dc.contributor.authorWang, B-
dc.contributor.authorHu, J-
dc.contributor.authorPan, Y-
dc.contributor.authorPan, T-
dc.contributor.authorWang, W-
dc.contributor.authorGuo, X-
dc.date.accessioned2020-11-23T08:21:41Z-
dc.date.available2020-11-23T08:21:41Z-
dc.date.issued2020-
dc.identifier.citationComputer Aided Geometric Design, 2020, v. 80, p. article no. 101874-
dc.identifier.issn0167-8396-
dc.identifier.urihttp://hdl.handle.net/10722/293779-
dc.description.abstractThe medial axis transform (MAT) of a 3D shape includes the set of centers and radii of the maximally inscribed spheres, and is a complete shape descriptor that can be used to reconstruct the original shape. It is a compact representation that jointly describes geometry, topology, and symmetry properties of a given shape. In this work, we present P2MAT-NET, a neural network which learns the pattern of sparse point clouds and transform them into spheres approximating MAT. The experimental results illustrate that P2MAT-NET demonstrates better performance than state-of-the-art methods in computing MAT from point clouds, in terms of MAT quality to approximate the 3D shapes. The computed MAT can be used as an intermediate descriptor for downstream applications such as 3D shape recognition from point clouds. Our results show that it can achieve competitive performance in recognition with state-of-the-art methods.-
dc.languageeng-
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/cagd-
dc.relation.ispartofComputer Aided Geometric Design-
dc.subjectMedial axis transform-
dc.subjectNeural networks-
dc.subjectPoint clouds-
dc.titleP2MAT-NET: Learning medial axis transform from sparse point clouds-
dc.typeArticle-
dc.identifier.emailWang, W: wenping@cs.hku.hk-
dc.identifier.authorityWang, W=rp00186-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.cagd.2020.101874-
dc.identifier.scopuseid_2-s2.0-85084417639-
dc.identifier.hkuros318929-
dc.identifier.volume80-
dc.identifier.spagearticle no. 101874-
dc.identifier.epagearticle no. 101874-
dc.identifier.isiWOS:000537812800012-
dc.publisher.placeNetherlands-
dc.identifier.issnl0167-8396-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats