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

Stefano Zorzi, Shabab Bazrafkan, Stefan Habenschuss, Friedrich Fraundorfer

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

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.

Originalspracheenglisch
TitelProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Herausgeber (Verlag)IEEE Computer Society Publications
Seiten1838-1847
Seitenumfang10
ISBN (elektronisch)9781665469463
DOIs
PublikationsstatusVeröffentlicht - 2022
Veranstaltung2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2022 - New Orleans, USA / Vereinigte Staaten
Dauer: 19 Juni 202224 Juni 2022

Konferenz

Konferenz2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
KurztitelCVPR 2022
Land/GebietUSA / Vereinigte Staaten
OrtNew Orleans
Zeitraum19/06/2224/06/22

ASJC Scopus subject areas

  • Software
  • Maschinelles Sehen und Mustererkennung

Fingerprint

Untersuchen Sie die Forschungsthemen von „PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren