Polygonal Building Extraction by Frame Field Learning



Published on


While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons. To help bridge the gap between deep network output and the format used in downstream tasks, we add a frame field output to a deep segmentation model for extracting buildings from remote sensing images. We train a deep neural network that aligns a predicted frame field to ground truth contours. This additional objective improves segmentation quality by leveraging multi-task learning and provides structural information that later facilitates polygonization; we also introduce a polygonization algorithm that that utilizes the frame field along with the raster segmentation.

Please cite our work using the BibTeX below.

    author    = {Girard, Nicolas and Smirnov, Dmitriy and Solomon, Justin and Tarabalka, Yuliya},
    title     = {Polygonal Building Extraction by Frame Field Learning},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {5891-5900}
Close Modal