@inproceedings{PB-VRVis-2022-019,
author = {Zorzi, Stefano and Bazrafkan, Shabab and Habenschuss, Stefan and Fraundorfer, Friedrich},
title = {PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images},
year = {2022},
booktitle = {IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)  2022},
editor = {n.n.},
url = {https://www.vrvis.at/publications/PB-VRVis-2022-019},
abstract = {While most state-of-the-art instance segmentation meth-
ods 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 di-
rectly extracts building vertices from an image and connects
them correctly to create precise polygons. The model pre-
dicts the connection strength between each pair of vertices
using a graph neural network and estimates the assign-
ments by solving a differentiable optimal transport problem.
Moreover, the vertex positions are optimized by minimiz-
ing a combined segmentation and polygonal angle differ-
ence loss. PolyWorld significantly outperforms the state of
the art in building polygonization and achieves not only no-
table quantitative results, but also produces visually pleas-
ing building polygons. Code and trained weights are pub-
licly available at https://github.com/zorzi-s/PolyWorldPretrainedNetwork.},
keywords = {Computer Vision, Pattern Recognition},
}