# DSM Building Shape Refinement from Combined Remote Sensing Images based on Wnet-cGANs

## TL;DR

This paper introduces a novel WNet-cGAN approach that refines digital surface models by fusing stereo DSMs with high-resolution panchromatic satellite images, enhancing building shape accuracy and edge sharpness.

## Contribution

It presents a new hybrid cGAN architecture that combines stereo DSMs and spectral images for improved DSM refinement and building shape delineation.

## Key findings

- Enhanced building outline accuracy
- Sharper and more rectangular building edges
- Effective fusion of DSMs and spectral images

## Abstract

We describe the workflow of a digital surface models (DSMs) refinement algorithm using a hybrid conditional generative adversarial network (cGAN) where the generative part consists of two parallel networks merged at the last stage forming a WNet architecture. The inputs to the so-called WNet-cGAN are stereo DSMs and panchromatic (PAN) half-meter resolution satellite images. Fusing these helps to propagate fine detailed information from a spectral image and complete the missing 3D knowledge from a stereo DSM about building shapes. Besides, it refines the building outlines and edges making them more rectangular and sharp.