A single image deep learning approach to restoration of corrupted remote sensing products
This addresses the issue of image corruption in remote sensing for applications like agricultural monitoring and disaster relief, but it is incremental as it builds on the Deep Image Prior methodology.
The paper tackles the problem of reconstructing missing information in corrupted remote sensing images by introducing a novel approach that uses only the corrupted image as input, eliminating the need for pre-trained networks or image databases, and it outperforms traditional single-image methods.
Remote sensing images are used for a variety of analyses, from agricultural monitoring, to disaster relief, to resource planning, among others. The images can be corrupted due to a number of reasons, including instrument errors and natural obstacles such as clouds. We present here a novel approach for reconstruction of missing information in such cases using only the corrupted image as the input. The Deep Image Prior methodology eliminates the need for a pre-trained network or an image database. It is shown that the approach easily beats the performance of traditional single-image methods.