NightVision: Generating Nighttime Satellite Imagery from Infra-Red Observations
This addresses a data gap for applications relying on visible satellite imagery at night, though it is incremental as it applies existing methods to a new domain.
The paper tackled the lack of nighttime visible satellite imagery by generating such images from infra-red observations using deep learning, achieving an SSIM of up to 86% on a test set.
The recent explosion in applications of machine learning to satellite imagery often rely on visible images and therefore suffer from a lack of data during the night. The gap can be filled by employing available infra-red observations to generate visible images. This work presents how deep learning can be applied successfully to create those images by using U-Net based architectures. The proposed methods show promising results, achieving a structural similarity index (SSIM) up to 86\% on an independent test set and providing visually convincing output images, generated from infra-red observations.