CDMM:Conditional Diffusion Model with Mamba for Low-light Underwater Image Enhancement

Underwater photography is frequently characterized by low contrast, blurred edge details, and color distortions, primarily due to inadequate lighting. These factors impede the acquisition and analysis of underwater imagery using computer vision techniques. In the domain of improving visibility in underwater images taken under dim lighting, existing studies usually result in the introduction of artifacts, the loss of edge details, and an increase in noise. This research introduces a novel approach grounded in a diffusion model intended to optimize the quality of underwater imagery taken in dim conditions, utilizing low-light images and Gaussian noise as inputs to produce enhanced outputs. To enhance the denoising process within the diffusion model, a TCM-Block has been integrated as the denoising component, thus elevating the quality of the resultant images. Furthermore, the diffusion process is guided by the original image to preserve edge details and enhance visual perception. The experimental results indicate that our approach surpasses eight alternative methods in six metrics ranks second in the seventh, and exhibits strong performance on images with varying degrees of low-light conditions, highlighting the considerable advantages of our approach. This study not only provides an effective technical solution for enhancing low-light underwater images but also presents a novel perspective on image processing in such environments, facilitated by the application of the diffusion model and the Mamba block.