The field of image restoration and enhancement is moving towards the development of unified models that can handle diverse degradation conditions, such as adverse weather, underwater, and rain streaks. Researchers are exploring innovative approaches, including continual learning, spectral-based spatial grouping, and degradation-aware conditional diffusion models, to improve the robustness and effectiveness of image restoration and enhancement techniques. These advancements have the potential to significantly improve the performance of downstream tasks, such as autonomous driving, underwater navigation, and visual perception. Notable papers in this area include: Continual Learning-Based Unified Model for Unpaired Image Restoration Tasks, which proposes a unified framework for image restoration using selective kernel fusion layers and elastic weight consolidation. DACA-Net: A Degradation-Aware Conditional Diffusion Network for Underwater Image Enhancement, which introduces a novel conditional diffusion-based restoration network with a Swin UNet backbone and degradation-guided adaptive feature fusion module.