LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizondepth along with room height...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 1644 - 1653
Hlavní autoři: Jiang, Zhigang, Xiang, Zhongzheng, Xu, Jinhua, Zhao, Ming
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract 3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizondepth along with room height can obtain omnidirectionalgeometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planar-geometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets. The code is publicly available at https://github.com/zhigangjiang/LGT-Net.
AbstractList 3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizondepth along with room height can obtain omnidirectionalgeometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planar-geometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets. The code is publicly available at https://github.com/zhigangjiang/LGT-Net.
Author Jiang, Zhigang
Xiang, Zhongzheng
Xu, Jinhua
Zhao, Ming
Author_xml – sequence: 1
  givenname: Zhigang
  surname: Jiang
  fullname: Jiang, Zhigang
  email: zigjiang@gmail.com
  organization: East China Normal University
– sequence: 2
  givenname: Zhongzheng
  surname: Xiang
  fullname: Xiang, Zhongzheng
  email: even_and_just@126.com
  organization: Yiwo Technology
– sequence: 3
  givenname: Jinhua
  surname: Xu
  fullname: Xu, Jinhua
  email: jhxu@cs.ecnu.edu.cn
  organization: East China Normal University
– sequence: 4
  givenname: Ming
  surname: Zhao
  fullname: Zhao, Ming
  email: zhaoming@123kanfang.com
  organization: Yiwo Technology
BookMark eNotztFKwzAUgOEoCm5zT6AXeYHWc5I2TbwbY85B0TGmeDeSJcGqbSSNlL69A7367z7-KbnoQucIuUXIEUHdLV-3u5IJKXMGjOUAWMEZmaIQZSFUIfg5mSAIngmF6orM-_4DADhDFEpOyFu93mdPLt3TTWdDiHSruxB12xzpLoSW1noMP4mu-tS0OjWho0OT3unahdalOGaLQUdH91F3vQ-xdZGesCHEz2ty6fVX7-b_nZGXh9V--ZjVz-vNclFnDQOeMmOV1ayyAtCiMnDa5tZ7rIypPBaV8YYpIz2rjqywrGSSWeVKayT3DpTgM3Lz5zbOucN3PG3G8aCkBOQF_wXopVTM
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.00170
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
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 1653
ExternalDocumentID 9880134
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 61175116
  funderid: 10.13039/501100001809
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-i203t-bd9da27d601d19b06653dff17bb7f147bfb29b8f27c24d25282d9e5db83fe0963
IEDL.DBID RIE
ISICitedReferencesCount 22
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754201087&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 02:15:10 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-bd9da27d601d19b06653dff17bb7f147bfb29b8f27c24d25282d9e5db83fe0963
PageCount 10
ParticipantIDs ieee_primary_9880134
PublicationCentury 2000
PublicationDate 2022-June
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.3938909
Snippet 3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient...
SourceID ieee
SourceType Publisher
StartPage 1644
SubjectTerms 3D from single images; Datasets and evaluation; Deep learning architectures and techniques; Photogrammetry and remote sensing; Recognition: detection
categorization
Deep learning
Estimation
Geometry
grouping and shape analysis; Vision applications and systems
Layout
Neural networks
retrieval; Robot vision; Scene analysis and understanding; Segmentation
Solid modeling
Three-dimensional displays
Title LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network
URI https://ieeexplore.ieee.org/document/9880134
WOSCitedRecordID wos000867754201087&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/eLvHCXMwlV07T8MwELbaioGJR4t4ywMjpnHSxDEbqtqCVEVRVVC3yo-z1KEJSlNQ_z12EgoDC5vlxdJ9tu6-8313CN1JZZ1QKCMCnuRkYFEnloIZEumYKiN9waASCk9ZksSLBU9b6H6vhQGAqvgMHtyy-svXudq6VFmf28tGg0EbtRmLaq3WPp8SWCYT8bhRx1GP94dv6cw1M3EFXL5ry0ndROJfM1QqFzI--t_hx6j3o8XD6d7LnKAWZKfoqAkecfM0N120mE7mJIHyEb9kOs8LnIrMwrteKTyzwTGeil2-LfHIPularYhdChZPIF9DWezI06coAM-_41gocFJXiPfQ63g0Hz6TZmwCWfleUBKpuRY-05Zqacql-1sJtDGUSckMHTBpIeAyNj5T_kD7oSVdmkOoZRwYsIwmOEOdLM_gHGFjg0ljCaNw_ayZioUnjKIyDkFIwZi8QF1nqOV73Rlj2djo8u_tK3TokKgLra5Rpyy2cIMO1Ee52hS3FZxfSy2iPA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZKQYKpQIt444ER0-ZVx2yoog8RoqgKqFtlx2epQxOUpqD-e-wkFAYWNsuLpfts3X3n--4QuhWJdkKe6BPoCUZcjTrRFEyRvvStRAmbUyiFwgENQ382Y1ED3W21MABQFp_BvVmWf_kyS9YmVdZl-rJZjruDds3krFqttc2oOJrL9Jlf6-OsHusO3qKpaWdiSrhs05jTMjOJf01RKZ3IsPW_4w9R50eNh6OtnzlCDUiPUasOH3H9OFdtNAtGMQmheMCTVGZZjiOeaoCXiwRPdXiMA77J1gV-0o-60itik4TFI8iWUOQb8vjJc8DxdyQLOQ6rGvEOeh0-xYMxqQcnkIXdcwoiJJPcplKTLWkxYX5XHKmURYWgynKp0CAw4SubJrYrbU_TLsnAk8J3FGhO45ygZpqlcIqw0uGk0pSRm47WNPF5j6vEEr4HXHBKxRlqG0PN36veGPPaRud_b9-g_XH8EsyDSfh8gQ4MKlXZ1SVqFvkartBe8lEsVvl1Ce0X7QelhQ
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=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=LGT-Net%3A+Indoor+Panoramic+Room+Layout+Estimation+with+Geometry-Aware+Transformer+Network&rft.au=Jiang%2C+Zhigang&rft.au=Xiang%2C+Zhongzheng&rft.au=Xu%2C+Jinhua&rft.au=Zhao%2C+Ming&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1644&rft.epage=1653&rft_id=info:doi/10.1109%2FCVPR52688.2022.00170&rft.externalDocID=9880134