UIEDP:Underwater Image Enhancement with Diffusion Prior
This work addresses the challenge of low-quality synthetic training data in underwater image enhancement, offering a domain-specific solution for clearer underwater imagery.
The paper tackles the problem of underwater image enhancement by proposing UIEDP, a framework that uses a pre-trained diffusion model as a prior to improve image quality, resulting in significant gains in metrics like no-reference image quality assessment.
Underwater image enhancement (UIE) aims to generate clear images from low-quality underwater images. Due to the unavailability of clear reference images, researchers often synthesize them to construct paired datasets for training deep models. However, these synthesized images may sometimes lack quality, adversely affecting training outcomes. To address this issue, we propose UIE with Diffusion Prior (UIEDP), a novel framework treating UIE as a posterior distribution sampling process of clear images conditioned on degraded underwater inputs. Specifically, UIEDP combines a pre-trained diffusion model capturing natural image priors with any existing UIE algorithm, leveraging the latter to guide conditional generation. The diffusion prior mitigates the drawbacks of inferior synthetic images, resulting in higher-quality image generation. Extensive experiments have demonstrated that our UIEDP yields significant improvements across various metrics, especially no-reference image quality assessment. And the generated enhanced images also exhibit a more natural appearance.