PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images

While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects instead of rasterized output. This paper introduces PolyWorld, a neural network that directly extracts...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1938 - 1947
Main Authors: Zorzi, Stefano, Bazrafkan, Shabab, Habenschuss, Stefan, Fraundorfer, Friedrich
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2022
Subjects:
Buildings
Codes
Computer network reliability
Computer vision
grouping and shape analysis
Image segmentation
Photogrammetry and remote sensing; Deep learning architectures and techniques; Segmentation
Predictive models
Satellites
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects instead of rasterized output. This paper introduces PolyWorld, a neural network that directly extracts building vertices from an image and connects them correctly to create precise polygons. The model predicts the connection strength between each pair of vertices using a graph neural network and estimates the assignments by solving a differentiable optimal transport problem. Moreover, the vertex positions are optimized by minimizing a combined segmentation and polygonal angle difference loss. PolyWorld significantly outperforms the state of the art in building polygonization and achieves not only notable quantitative results, but also produces visually pleasing building polygons. Code and trained weights are publicly available at https://thub.com/zorzis/yWorl-PoldPretrainedNetwork.
AbstractList While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects instead of rasterized output. This paper introduces PolyWorld, a neural network that directly extracts building vertices from an image and connects them correctly to create precise polygons. The model predicts the connection strength between each pair of vertices using a graph neural network and estimates the assignments by solving a differentiable optimal transport problem. Moreover, the vertex positions are optimized by minimizing a combined segmentation and polygonal angle difference loss. PolyWorld significantly outperforms the state of the art in building polygonization and achieves not only notable quantitative results, but also produces visually pleasing building polygons. Code and trained weights are publicly available at https://thub.com/zorzis/yWorl-PoldPretrainedNetwork.
Author Zorzi, Stefano
Fraundorfer, Friedrich
Habenschuss, Stefan
Bazrafkan, Shabab
Author_xml – sequence: 1
  givenname: Stefano
  surname: Zorzi
  fullname: Zorzi, Stefano
  email: stefano.zorzi@icg.tugraz.at
  organization: Graz University of Technology
– sequence: 2
  givenname: Shabab
  surname: Bazrafkan
  fullname: Bazrafkan, Shabab
  email: sbazrafkan@blackshark.ai
  organization: Blackshark.ai
– sequence: 3
  givenname: Stefan
  surname: Habenschuss
  fullname: Habenschuss, Stefan
  email: shabenschuss@blackshark.ai
  organization: Blackshark.ai
– sequence: 4
  givenname: Friedrich
  surname: Fraundorfer
  fullname: Fraundorfer, Friedrich
  email: fraundorfer@icg.tugraz.at
  organization: Graz University of Technology
BookMark eNotj81OAjEURqvRREGeQBd9gcHblum07pQgkhAk_rEknektVMsM6ZQgby9GV99ZnJzk65CzuqmRkBsGfcZA3w4_5i85l0r1OXDeB2BKn5AOkzIfSD2Q4pRcMpAik5rpC9Jr208AEJwxqdUlWcybcFg0Mdg7-ourpjaBPux8sL5e0dF3iqZKvqnp3qc1HUezXdMZ7uLRmmHaN_Grpb6mryZhCD4hnWzMCtsrcu5MaLH3v13y_jh6Gz5l0-fxZHg_zTwHkbKylIUQogSjcls6VIUsc1eZ0gqHMmdWGdRQVKoqrJTcgUPrquOTwhWIlRVdcv3X9Yi43Ea_MfGw1ErBgOfiB0jrVjM
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.00189
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 1947
ExternalDocumentID 9880425
Genre orig-research
GrantInformation_xml – fundername: BMDW
  funderid: 10.13039/501100012416
– fundername: SFG
  funderid: 10.13039/501100007945
– fundername: FFG
  funderid: 10.13039/501100004955
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-bb67333b0a85dbfe876b5fcabd3fe651d8ae907c8c7d662f0fedfc9197f7eecd3
IEDL.DBID RIE
ISICitedReferencesCount 78
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754202010&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 02:15:11 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-bb67333b0a85dbfe876b5fcabd3fe651d8ae907c8c7d662f0fedfc9197f7eecd3
PageCount 10
ParticipantIDs ieee_primary_9880425
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 2.529208
Snippet While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise...
SourceID ieee
SourceType Publisher
StartPage 1938
SubjectTerms Buildings
Codes
Computer network reliability
Computer vision
grouping and shape analysis
Image segmentation
Photogrammetry and remote sensing; Deep learning architectures and techniques; Segmentation
Predictive models
Satellites
Title PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
URI https://ieeexplore.ieee.org/document/9880425
WOSCitedRecordID wos000867754202010&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/eLvHCXMwlV07T8MwELbaioGpQIt4ywMjoXGc-MFI1QJLFfHsVsX2GVWiKWpSBP8eO4kKAwubFUWKZJ_tu8v3QOhccKm1spELXuIKFGJNIGKjAgaEE2t5yExcmU3wyURMpzJtoYsNFwYAKvAZXPph9S_fLPXat8oG0gWbi7E2anPOa67Wpp9CXSXDpGjYcSSUg-Fzeu_FTDyAK_KynMR7uf_yUKmukHH3fx_fQf0fLh5ON7fMLmpBvoe6TfKIm61Z9NBLunz7qqAxV9gPX32Kja8b12s8-ixXNYcB-9YrvvFC1dhLc7i3JjUWvMDzHD9klUZnCfhu4c6aoo-exqPH4W3QuCYE8yikZaAU45RSFWYiMcqCO-5UYnWmDLXAEmJEBq4i1kJzw1hkQwvGakkktxxAG7qPOvkyhwOEXa5nFFE0VAnEsZHCxFQzoqXNMqOEOUQ9P0-z91oYY9ZM0dHfj4_Rtl-IGmd1gjrlag2naEt_lPNidVat5jfSr6PG
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LT8IwGG8QTfSECsa3PXh0sq5bHx4lIERciKJyI-vLkOgwbBj97223BT148dYsS5a0X9vv-_Z7AHDOKJdSmMAGL7IFCjLKY6ESHtGIImOoT1RYmE3QOGaTCR_VwMWKC6O1LsBn-tINi3_5ai6XrlXW5jbYbIytgfUoDANUsrVWHRVsaxnCWcWPQz5vd55G907OxEG4AifMiZyb-y8XleIS6TX-9_lt0Pph48HR6p7ZATWd7oJGlT7CanNmTfA8mr9-FeCYK-iGLy7JhteV7zXsfuaLksUAXfMV3jipaujEOexbcYkGz-AshQ9JodKZazh4s6dN1gKPve640_cq3wRvFvg494QgFGMs_IRFShhtDzwRGZkIhY0mEVIs0bYmlkxSRUhgfKOVkRxxaqjWUuE9UE_nqd4H0GZ7SiCBfRHpMFScqRBLgiQ3SaIEUweg6eZp-l5KY0yrKTr8-_EZ2OyP74bT4SC-PQJbblFK1NUxqOeLpT4BG_Ijn2WL02JlvwGCrqcN
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=PolyWorld%3A+Polygonal+Building+Extraction+with+Graph+Neural+Networks+in+Satellite+Images&rft.au=Zorzi%2C+Stefano&rft.au=Bazrafkan%2C+Shabab&rft.au=Habenschuss%2C+Stefan&rft.au=Fraundorfer%2C+Friedrich&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1938&rft.epage=1947&rft_id=info:doi/10.1109%2FCVPR52688.2022.00189&rft.externalDocID=9880425