CPDM: Content-preserving diffusion model for underwater image enhancement

Underwater image enhancement (UIE) is challenging since image degradation in aquatic environments is complicated and changing over time. Existing mainstream methods rely on either physical-model or data-driven, suffering from performance bottlenecks due to changes in imaging conditions or training instability. In this article, we attempt to adapt the diffusion model to the UIE task and propose a Content-Preserving Diffusion Model (CPDM) to address the above challenges. CPDM first leverages a diffusion model as its fundamental model for stable training and then designs a content-preserving framework to deal with changes in imaging conditions. Specifically, we construct a conditional input module by adopting both the raw image and the difference between the raw and noisy images as the input at each time step of the diffusion process, which can enhance the model's adaptability by considering the changes involving the raw images in underwater environments. To preserve the essential content of the raw images, we construct a content compensation module for content-aware training by extracting low-level image features of the raw images as compensation for each down block. We conducted tests on the LSUI, UIEB, and EUVP datasets, and the results show that CPDM outperforms state-of-the-art methods in both subjective and objective metrics, achieving the best overall performance. The GitHub link for the code is https://github.com/GZHU-DVL/CPDM.