Super-Resolving Beyond Satellite Hardware Using Realistically Degraded Images
This addresses the problem of enhancing satellite imagery for remote sensing applications, but it is incremental as it applies an existing method to new data.
The paper tested deep super-resolution (SR) on realistically degraded satellite images, finding that a state-of-the-art SR technique (EDSR) can recover encoded pixel data under certain conditions, with performance varying by geography, and suggested custom training could improve reconstruction.
Modern deep Super-Resolution (SR) networks have established themselves as valuable techniques in image reconstruction and enhancement. However, these networks are normally trained and tested on benchmark image data that lacks the typical image degrading noise present in real images. In this paper, we test the feasibility of using deep SR in real remote sensing payloads by assessing SR performance in reconstructing realistically degraded satellite images. We demonstrate that a state-of-the-art SR technique called Enhanced Deep Super-Resolution Network (EDSR), without domain specific pre-training, can recover encoded pixel data on images with poor ground sampling distance, provided the ground resolved distance is sufficient. However, this recovery varies amongst selected geographical types. Our results indicate that custom training has potential to further improve reconstruction of overhead imagery, and that new satellite hardware should prioritise optical performance over minimising pixel size as deep SR can overcome a lack of the latter but not the former.