Frustum PointNets for 3D Object Detection from RGB-D Data

In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challeng...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 918 - 927
Hlavní autori: Qi, Charles R., Liu, Wei, Wu, Chenxia, Su, Hao, Guibas, Leonidas J.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2018
Predmet:
Detectors
Image segmentation
Object detection
Proposals
Three-dimensional displays
Two dimensional displays
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.
AbstractList In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.
Author Qi, Charles R.
Guibas, Leonidas J.
Liu, Wei
Wu, Chenxia
Su, Hao
Author_xml – sequence: 1
  givenname: Charles R.
  surname: Qi
  fullname: Qi, Charles R.
– sequence: 2
  givenname: Wei
  surname: Liu
  fullname: Liu, Wei
– sequence: 3
  givenname: Chenxia
  surname: Wu
  fullname: Wu, Chenxia
– sequence: 4
  givenname: Hao
  surname: Su
  fullname: Su, Hao
– sequence: 5
  givenname: Leonidas J.
  surname: Guibas
  fullname: Guibas, Leonidas J.
BookMark eNotzE1Pg0AQANDVaGKtnD142T8AzuwXs0cFW00a2zTqtVlgSGgEDGwP_ntN9PRu71pcDOPAQtwiZIjg74uP3T5TgJQBIKgzkfic0Gpyzijw52KB4HTqPPorkczzEQCUI03GLoRfTac5nnq5G7shvnKcZTtOUpdyWx25jrLk-Es3DrKdxl7u149pKcsQw424bMPnzMm_S_G-enorntPNdv1SPGzSDnMbU6pa7Wttbe40KNNYbtkRcEPe6FpjqExgDJ5yS-TRMlBbG19hsLpuVK2X4u7v7Zj58DV1fZi-D2RzUgD6B4y8RxU
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00102
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
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781538664209
1538664208
EISSN 1063-6919
EndPage 927
ExternalDocumentID 8578200
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-8bf39c355763024d5efe680ed8943c31ab4ae1a987588915e08fc49b1a53cd2c3
IEDL.DBID RIE
ISICitedReferencesCount 1911
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843601005&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 02:52:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-8bf39c355763024d5efe680ed8943c31ab4ae1a987588915e08fc49b1a53cd2c3
PageCount 10
ParticipantIDs ieee_primary_8578200
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 2.6401565
Snippet In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often...
SourceID ieee
SourceType Publisher
StartPage 918
SubjectTerms Detectors
Image segmentation
Object detection
Proposals
Three-dimensional displays
Two dimensional displays
Title Frustum PointNets for 3D Object Detection from RGB-D Data
URI https://ieeexplore.ieee.org/document/8578200
WOSCitedRecordID wos000457843601005&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/eLvHCXMwlV09T8MwELVKxcDER4v4lgdGTOO6ie2VhsKASlRB1a3yx0XqQIpal9-PL40KAwtbnMk6O3l35_eeCbnVPtMqAhPzXlg20NawuEs0MxpE6oSRoma7T1_keKxmM120yN1OCwMANfkM7vGxPsv3S7fBVllPofd6Egv0PSnlVqu166f0MyVUc0KGYxErmziNxs2HJ7o3nBYT5HIheZJjG-XXdSo1mowO_zePI9L9keXRYgc4x6QF1Qk5bPJI2nyl6w7RIxRSbD5osVxUYQxhTWNqSkVOXy22XWgOoWZgVRTVJXTy9MBymptguuR99Pg2fGbNFQlsEXE_MGVLoV3MGeJvIqKtT6GETCXg0VbdCW7swAA3OlYlSmmeQqJKF1eEm1Q433filLSrZQVnhDqZWadTablCFzGpBqVHczurY6HZB3NOOhiJ-efWBWPeBOHi79eX5ABDvSVVXZF2WG3gmuy7r7BYr27qpfsGZuaWAw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWqggRTgRbxjQdGTOM4H_ZKQymihKgqVbfKHxepQ1PUpvx-7DQqDCxscSbr7OTdnd97RuhOmEhwC0zEGKZIIJQkdpcIIgWwUDMZs4rtPhnGacqnU5E10P1OCwMAFfkMHtxjdZZvlnrjWmVd7rzXPVug74VB4NOtWmvXUfEjznh9RubGzNY2diK1nw_1RLc3yUaOzeXok9Q1Un5dqFLhSb_1v5kcoc6PMA9nO8g5Rg0oTlCrziRx_Z2u20j0nZRis8DZcl6UKZRrbJNTzBL8rlzjBSdQVhysAjt9CR49P5IEJ7KUHfTRfxr3BqS-JIHMLfKXhKucCW2zBvujsHhrQsgh4h4YZ6yuGZUqkEClsHUJ54KG4PFc2zWhMmTa-JqdomaxLOAMYR1HSoswVpQ7H7GYB7lx9nZK2FLTB3mO2i4Ss8-tD8asDsLF369v0cFg_DacDV_S10t06MK-pVhdoWa52sA12tdf5Xy9uqmW8Rtp3ZlK
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=Frustum+PointNets+for+3D+Object+Detection+from+RGB-D+Data&rft.au=Qi%2C+Charles+R.&rft.au=Liu%2C+Wei&rft.au=Wu%2C+Chenxia&rft.au=Su%2C+Hao&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=918&rft.epage=927&rft_id=info:doi/10.1109%2FCVPR.2018.00102&rft.externalDocID=8578200