Conditional Progressive Generative Adversarial Network for satellite image generation
This work addresses computational challenges in generating detailed satellite imagery for applications like flood detection, though it is incremental as it builds on existing GAN and auto-encoder techniques.
The paper tackled generating large high-resolution satellite images by formulating it as an iterative tile completion problem, introducing a conditional progressive GAN that uses a Wasserstein auto-encoder to encode adjacent tiles, and validated the method on UNOSAT flood detection data with realistic quality assessment.
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.