Polygonal Building Segmentation by Frame Field Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Polygonal Building Segmentation by Frame Field Learning

Abstract

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 utilizes the frame field along with the raster segmentation. Our code is available at https://github.com/Lydorn/Polygonization-by-Frame-Field-Learning.
Fichier principal
Vignette du fichier
archive.pdf (12.87 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02548545 , version 1 (27-04-2020)
hal-02548545 , version 2 (31-03-2021)

Identifiers

  • HAL Id : hal-02548545 , version 2

Cite

Nicolas Girard, Dmitriy Smirnov, Justin Solomon, Yuliya Tarabalka. Polygonal Building Segmentation by Frame Field Learning. CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2021, Pittsburg / Virtual, United States. ⟨hal-02548545v2⟩
331 View
370 Download

Share

Gmail Facebook X LinkedIn More