# CG-Net: Conditional GIS-aware Network for Individual Building Segmentation in VHR SAR Images

arXiv: https://arxiv.org/abs/2011.08362 · HTML: https://mlsanity.com/paper/2011.08362/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Building extraction with vision transformer](https://mlsanity.com/paper/2111.15637/) (2021)
- [Large-scale Building Height Retrieval from Single SAR Imagery based on Bounding Box Regression Networks](https://mlsanity.com/paper/2111.09460/) (2021)
- [HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images](https://mlsanity.com/paper/2309.16486/) (2023)
- [QuickQuakeBuildings: Post-earthquake SAR-Optical Dataset for Quick Damaged-building Detection](https://mlsanity.com/paper/2312.06587/) (2023)
- [Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved](https://mlsanity.com/paper/2309.08042/) (2023)
- [Building Floor Number Estimation from Crowdsourced Street-Level Images: Munich Dataset and Baseline Method](https://mlsanity.com/paper/2505.18021/) (2025)
- [Heterogeneous Feature Distillation Network for SAR Image Semantic Segmentation](https://mlsanity.com/paper/2210.08988/) (2022)
- [A Deep Learning framework for building damage assessment using VHR SAR and geospatial data: demonstration on the 2023 Turkiye Earthquake](https://mlsanity.com/paper/2506.22338/) (2025)

## Abstract (arXiv)

Object retrieval and reconstruction from very high resolution (VHR) synthetic aperture radar (SAR) images are of great importance for urban SAR applications, yet highly challenging owing to the complexity of SAR data. This paper addresses the issue of individual building segmentation from a single VHR SAR image in large-scale urban areas. To achieve this, we introduce building footprints from GIS data as complementary information and propose a novel conditional GIS-aware network (CG-Net). The proposed model learns multi-level visual features and employs building footprints to normalize the features for predicting building masks in the SAR image. We validate our method using a high resolution spotlight TerraSAR-X image collected over Berlin. Experimental results show that the proposed CG-Net effectively brings improvements with variant backbones. We further compare two representations of building footprints, namely complete building footprints and sensor-visible footprint segments, for our task, and conclude that the use of the former leads to better segmentation results. Moreover, we investigate the impact of inaccurate GIS data on our CG-Net, and this study shows that CG-Net is robust against positioning errors in GIS data. In addition, we propose an approach of ground truth generation of buildings from an accurate digital elevation model (DEM), which can be used to generate large-scale SAR image datasets. The segmentation results can be applied to reconstruct 3D building models at level-of-detail (LoD) 1, which is demonstrated in our experiments.