# Polygonal Building Segmentation by Frame Field Learning

arXiv: https://arxiv.org/abs/2004.14875 · HTML: https://mlsanity.com/paper/2004.14875/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Accurate Polygonal Mapping of Buildings in Satellite Imagery](https://mlsanity.com/paper/2208.00609/) (2022)
- [Polygonizer: An auto-regressive building delineator](https://mlsanity.com/paper/2304.04048/) (2023)
- [Investigating transformers in the decomposition of polygonal shapes as point collections](https://mlsanity.com/paper/2108.07533/) (2021)
- [GeoFormer: A Multi-Polygon Segmentation Transformer](https://mlsanity.com/paper/2411.16616/) (2024)
- [Deep Learning and Earth Observation to Support the Sustainable Development Goals](https://mlsanity.com/paper/2112.11367/) (2021)
- [Brightearth roads: Towards fully automatic road network extraction from satellite imagery](https://mlsanity.com/paper/2406.14941/) (2024)
- [Fields of the Planet: Field Boundary Mapping Beyond 10m](https://mlsanity.com/paper/2607.04449/) (2026)

## Abstract (arXiv)

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.