The field of image restoration and enhancement is rapidly evolving, with a focus on developing innovative methods to improve the quality of images captured in various environments. Recent developments have seen a shift towards leveraging advanced neural network architectures, such as Mamba, to model complex dependencies and restore high-frequency details in images. Additionally, there is a growing interest in exploring the potential of single-scale features and uncertainty-aware approaches to enhance image quality. Notably, researchers are also investigating the application of optics-driven neural networks to address the unique challenges posed by metalens endoscopy. Overall, the field is moving towards more efficient, effective, and specialized solutions for various image restoration and enhancement tasks. Noteworthy papers include: UIS-Mamba, which proposes a novel underwater instance segmentation model using Mamba, and EPANet, which introduces an efficient path aggregation network for underwater fish detection. RetinexDual is also notable for its Retinex theory-based framework for generalized Ultra-High-Definition Image Restoration.