Vol. 127, No. 4 * Pages 421–504 * October - December 2023

Many image-based recognition tasks are highly susceptible to different types of natural phenomena like foggy weather, snow, or rain. The participating media will likely obscure important details necessary for these algorithms to work correctly. Still, these aspects could be recovered in certain situations with prior information about the underlying light interactions. This could be done with certain heuristics or with the nowadays popular deep-learning based methods. In this paper, we review and compare the results of two approaches to remove or scale down the effects of foggy weather. We also examine how these results can be applied to high resolution satellite images of land surfaces.