PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) S. 77 - 85
Hauptverfasser: Charles, R. Qi, Hao Su, Mo Kaichun, Guibas, Leonidas J.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2017
Schlagworte:
Computer architecture
Feature extraction
Machine learning
Semantics
Shape
Three-dimensional displays
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
AbstractList Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
Author Charles, R. Qi
Hao Su
Mo Kaichun
Guibas, Leonidas J.
Author_xml – sequence: 1
  givenname: R. Qi
  surname: Charles
  fullname: Charles, R. Qi
  organization: Stanford Univ., Stanford, CA, USA
– sequence: 2
  surname: Hao Su
  fullname: Hao Su
  organization: Stanford Univ., Stanford, CA, USA
– sequence: 3
  surname: Mo Kaichun
  fullname: Mo Kaichun
  organization: Stanford Univ., Stanford, CA, USA
– sequence: 4
  givenname: Leonidas J.
  surname: Guibas
  fullname: Guibas, Leonidas J.
  organization: Stanford Univ., Stanford, CA, USA
BookMark eNpNjMtOwzAURA0qEm1hx46NfyDhXtvxgx1KeUkRVLy2lXGuK6PWqZJs-HuqwoLVHM0ZzYxNcpeJsQuEEhHcVf2xfCkFoClRH7EZVtJqUJVRx2yKoGWhHbrJPz5ls2H4AhDSCJiyZtmlPD7ReM0XRDvekO9zymveZX5Q_JXGgceu53LB640fhhRT8GPaD3xu93q9pTweijN2Ev1moPO_nLP3u9u3-qFonu8f65umSELhWEShjHWfaEnYEJST2ovQmhZcRIhSkDQBbMTWChQymAjatMYpLysZNEk5Z5e_v4mIVrs-bX3_vbLgnHJO_gBw8E5o
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2017.16
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 1538604574
9781538604571
EISSN 1063-6919
EndPage 85
ExternalDocumentID 8099499
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i241t-f24789b18e28cc4936a2cd7d09f10f32e37c08f1d82123c7f067d794a353c6e33
IEDL.DBID RIE
ISICitedReferencesCount 4470
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418371400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Wed Aug 27 02:33:38 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i241t-f24789b18e28cc4936a2cd7d09f10f32e37c08f1d82123c7f067d794a353c6e33
PageCount 9
ParticipantIDs ieee_primary_8099499
PublicationCentury 2000
PublicationDate 2017-07
PublicationDateYYYYMMDD 2017-07-01
PublicationDate_xml – month: 07
  year: 2017
  text: 2017-07
PublicationDecade 2010
PublicationTitle 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublicationTitleAbbrev CVPR
PublicationYear 2017
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0023720
ssj0003211698
Score 2.6222107
Snippet Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or...
SourceID ieee
SourceType Publisher
StartPage 77
SubjectTerms Computer architecture
Feature extraction
Machine learning
Semantics
Shape
Three-dimensional displays
Title PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
URI https://ieeexplore.ieee.org/document/8099499
WOSCitedRecordID wos000418371400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JTwIxGG2AePCECsY9PXi00pnOdPEKEg-GTNzCjZQuhIMdAoO_37YMY0y8eGu-SZpJvzTvfVsfALcsEbnGKkeSU4s84inkFxIRnluuPOHNqI1iE2wy4dOpKFrgrpmFMcbE5jNzH5axlq9LtQ2psgH3dMYz9DZoM8Z2s1pNPoX4SIaKpoKQBvWVWOmkBFGRiKbpXQyGH8VLaOoKqZVfoioRU8bd__3NEej_DOfBooGdY9Ay7gR0azYJ67u68aa9YMPe1gPPRbl01cRUD3BkzArWj6suYOlg_ARfTbWBnsdCMoJRLzN0EkXnQen87mbxWQ8ruT54Hz--DZ9QLaeAlh6mK2TTjHExT7hJuVKZIFSmSjONhU2wJakhTGFuE80DnClmPZBpf10lyYmihpBT0HGlM2cAYj33PBJja5kP36SUSmSKM-3jEynmFJ-DXjiv2Wr3YsasPqqLv82X4DB4Y9cEewU61XprrsGB-qqWm_VNdPM3J9Wk9Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8IwGG4QTfSECsZve_BoZVu3fngFCUZciKLhRko_CAc3AsPfb1vGjIkXb827pFn6pnme96sPALc05IkKZIIEIwZZxJPILgTCLDFMWsIbE-PFJmiasvGYD2vgrpqF0Vr75jN975a-lq9yuXapsjazdMYy9B2wm8RxFG6mtaqMCraxDOFVDSFy-iu-1kkwIjzkVds7b3c-hq-urcslV37JqnhU6TX-9z-HoPUzngeHFfAcgZrOjkGj5JOwvK0ra9pKNmxtTTAY5vOsSHXxALtaL2D5vOoM5hn0n-CbLlbQMlmIu9ArZrpeIu8-KDK7u559luNKWQu89x5HnT4qBRXQ3AJ1gUwUU8anIdMRkzLmmIhIKqoCbsLA4EhjKgNmQsUcoElqLJQpe2EFTrAkGuMTUM_yTJ8CGKipZZJBYAy1AZwQQvJYMqpshCL4lARnoOnOa7LYvJkxKY_q_G_zDdjvj14Gk8FT-nwBDpxnNi2xl6BeLNf6CuzJr2K-Wl57l38D7k6oPA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=2017+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=PointNet%3A+Deep+Learning+on+Point+Sets+for+3D+Classification+and+Segmentation&rft.au=Charles%2C+R.+Qi&rft.au=Hao+Su&rft.au=Mo+Kaichun&rft.au=Guibas%2C+Leonidas+J.&rft.date=2017-07-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=77&rft.epage=85&rft_id=info:doi/10.1109%2FCVPR.2017.16&rft.externalDocID=8099499
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon