The field of image restoration and remote sensing is rapidly advancing with the development of new deep learning models and techniques. Researchers are focusing on improving the accuracy and efficiency of image restoration methods, particularly in adverse weather conditions. The use of attention mechanisms, multimodal fusion, and diffusion models are some of the key trends in this area. These innovations have the potential to significantly improve the performance of various applications such as autonomous driving, weather forecasting, and remote sensing. Noteworthy papers in this area include Joint Retrieval of Cloud properties using Attention-based Deep Learning Models, which introduced a compact UNet-based model that employs attention mechanisms to reduce errors in thick, overlapping cloud regions, and Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal, which proposed a novel multimodal diffusion bridge architecture for effective cloud removal. Additionally, SnapPix: Efficient-Coding--Inspired In-Sensor Compression for Edge Vision proposed a sensor-algorithm co-designed system for efficient image acquisition on the edge.