3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scan...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 9224 - 9232
Hlavní autori: Graham, Benjamin, Engelcke, Martin, Maaten, Laurens van der
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2018
Predmet:
Convolution
Convolutional codes
Image segmentation
Memory management
Semantics
Stationary state
Three-dimensional displays
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SS-CNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.
AbstractList Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SS-CNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.
Author Engelcke, Martin
Graham, Benjamin
Maaten, Laurens van der
Author_xml – sequence: 1
  givenname: Benjamin
  surname: Graham
  fullname: Graham, Benjamin
– sequence: 2
  givenname: Martin
  surname: Engelcke
  fullname: Engelcke, Martin
– sequence: 3
  givenname: Laurens van der
  surname: Maaten
  fullname: Maaten, Laurens van der
BookMark eNotjstOwzAURA0CiVKyZsEmP5BwHT_vEgVakCpABNhWjmODIXWqJKXi7wmC1Yx0RkdzSo5iFx0h5xRySgEvy9fHp7wAqnMAlPSAJKg0FUxLyQvAQzKjIFkmkeIJSYbhAwAKqZnmYkaW7Dqt3MbEMdipvG1cHM0Yupjuw_ieVrt6YsF3bZNWW9MPLi27-NW1u9-NadN7N-67_nM4I8fetINL_nNOXhY3z-VttnpY3pVXqyxQJcZM8EKhReYtd2C9VzU1ijNfoK-1mW5J5lkDaEFZUdeOS6mc4opzbWvbIJuTiz9vcM6tt33YmP57rYVCEMh-AKOATro
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00961
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
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
EISBN 9781538664209
1538664208
EISSN 1063-6919
EndPage 9232
ExternalDocumentID 8579059
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i175t-54279c93fc4e0cff7b1a743f29fb8a02663f3d09c07c5bbe4667e747448cbcd93
IEDL.DBID RIE
ISICitedReferencesCount 1347
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843609041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:52:16 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-54279c93fc4e0cff7b1a743f29fb8a02663f3d09c07c5bbe4667e747448cbcd93
PageCount 9
ParticipantIDs ieee_primary_8579059
PublicationCentury 2000
PublicationDate 2018-Jun
PublicationDateYYYYMMDD 2018-06-01
PublicationDate_xml – month: 06
  year: 2018
  text: 2018-Jun
PublicationDecade 2010
PublicationTitle 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683845
ssj0003211698
Score 2.636467
Snippet Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is...
SourceID ieee
SourceType Publisher
StartPage 9224
SubjectTerms Convolution
Convolutional codes
Image segmentation
Memory management
Semantics
Stationary state
Three-dimensional displays
Title 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
URI https://ieeexplore.ieee.org/document/8579059
WOSCitedRecordID wos000457843609041&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/eLvHCXMwlV07b8IwED4B6tCJtlC19CEPHZuS4ODHTEs7IdSX2FDsnCskCIjX7-85sWDp0s2OZMX5HNv3-O4O4MGvsXRJGnkOTZTaXEaZyUSkshRNqpBzVGWxCTkaqclEj2vweIiFQcSSfIZPvln68vOl3XlTWVf1fTopXYe6lKKK1TrYU3pCcRU8ZL7PSbMRWoVsPkmsu4Pv8bvncnnypC6TYh_LqZS3ybD5v3mcQfsYlsfGhwvnHGpYXEAzyJEs7NJNC175M_vABWE2s9T4WYT4ooJ5qyujs8InvXDLOQ1akWKLjF6wD_9gNmejihq-acPX8OVz8BaFggnRjKSAbdRPe1JbzZ1NMbbOSZNkJCG4nnZGZQSR4I7nsbaxtH1jMBVCIukTpKJZY3PNL6FRLAu8AsazBJG-xwnvp-TOOBpEG5ZOw0Qol19Dy-MyXVU5MaYBks7fj2_g1ANfUaxuobFd7_AOTux-O9us78uF_AUQR58t
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZKQYKpQIt444GR0CR2HHsulCJKVEFB3arEOaNKfamv3885sdqFhc2JZCW5i-17fPcdIfdWx7EJuGcxNB7XeeylWSo8mXLIuATGQBbNJuIkkYOB6lXIw7YWBgAK8Bk82mGRy89nem1DZU0ZWToptUf2I85Dv6zW2kZUQiGZdDkye83QtxFKOj6fwFfN1nfvw6K5LHxSFbTYu4YqxXnSrv3vTY5JY1eYR3vbI-eEVGB6SmrOkqRunS7r5IU90U-YoNRGGgc_E1dhNKU27kpxt7C0F2Y2xklzdG2B4gM27i9MxzQpweHLBvlqP_dbHc-1TPBGaAesvIiHsdKKGc3B18bEWZCijWBCZTKZoogEMyz3lfZjHWUZcCFiQI8CnTSd6VyxM1KdzqZwTihLAwD8HiNsppKZzOAkXLK4HwZCmvyC1K1chvOSFWPoRHL59-07ctjpv3eH3dfk7YocWSWUgKtrUl0t1nBDDvRmNVoubgul_gKGwKJ0
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%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=3D+Semantic+Segmentation+with+Submanifold+Sparse+Convolutional+Networks&rft.au=Graham%2C+Benjamin&rft.au=Engelcke%2C+Martin&rft.au=Maaten%2C+Laurens+van+der&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=9224&rft.epage=9232&rft_id=info:doi/10.1109%2FCVPR.2018.00961&rft.externalDocID=8579059