# Regularization of Building Boundaries in Satellite Images using Adversarial and Regularized Losses

arXiv: https://arxiv.org/abs/2007.11840 · HTML: https://mlsanity.com/paper/2007.11840/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images](https://mlsanity.com/paper/2111.15491/) (2021)
- [MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images](https://mlsanity.com/paper/2104.02846/) (2021)
- [PolyR-CNN: R-CNN for end-to-end polygonal building outline extraction](https://mlsanity.com/paper/2407.14912/) (2024)
- [BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction](https://mlsanity.com/paper/2303.00300/) (2023)

## Abstract (arXiv)

In this paper we present a method for building boundary refinement and regularization in satellite images using a fully convolutional neural network trained with a combination of adversarial and regularized losses. Compared to a pure Mask R-CNN model, the overall algorithm can achieve equivalent performance in terms of accuracy and completeness. However, unlike Mask R-CNN that produces irregular footprints, our framework generates regularized and visually pleasing building boundaries which are beneficial in many applications.