Conditional Progressive Generative Adversarial Network for satellite image generation

TL;DR

This paper introduces a scalable conditional progressive GAN approach that generates high-resolution satellite images by iteratively completing missing image corners, leveraging latent encoding and auto-encoders for realistic data synthesis.

Contribution

The work presents a novel conditional progressive GAN framework that efficiently generates detailed high-resolution satellite images through iterative completion and latent encoding.

Findings

Effective generation of high-resolution satellite images

Successful image completion with missing corners

Validation on UNOSAT flood detection dataset

Abstract

Image generation and image completion are rapidly evolving fields, thanks to machine learning algorithms that are able to realistically replace missing pixels. However, generating large high resolution images, with a large level of details, presents important computational challenges. In this work, we formulate the image generation task as completion of an image where one out of three corners is missing. We then extend this approach to iteratively build larger images with the same level of detail. Our goal is to obtain a scalable methodology to generate high resolution samples typically found in satellite imagery data sets. We introduce a conditional progressive Generative Adversarial Networks (GAN), that generates the missing tile in an image, using as input three initial adjacent tiles encoded in a latent vector by a Wasserstein auto-encoder. We focus on a set of images used by the United Nations Satellite Centre (UNOSAT) to train flood detection tools, and validate the quality of synthetic images in a realistic setup.