Multiple adverse weather image restoration: A review

Adverse weather conditions significantly impact the machine vision perception of unmanned platforms such as drones and autonomous vehicles. Therefore, restoring and enhancing images affected by these conditions is crucial. However, there is a lack of a comprehensive systematic review on the latest research progress in unified weather image restoration under all-in-one weather conditions and other factors. In this paper, we survey recent progress in various network architectures for multitask image restoration. Specifically, we review and compare different methods including, U-Net, GAN, Transformer, and U-Net/Transformer hybrids. Additionally, we evaluate publicly available datasets for single-task scenarios and compare the performance of these methods comprehensively, and analyze corresponding evaluation metrics. Based on these findings, we believe that Transformer and U-Net models are particularly promising for multi-task image restoration. Nevertheless, further research is needed to fully explore this area. Researchers can improve the image restoration effect from aspects such as data dynamic flow, encoder-decoder internal structure, etc. These insights contribute to advancing image acquisition technologies and addressing challenges in military image information retrieval, including military reconnaissance, terrain analysis, target identification, and battlefield surveillance.