Underwater image enhancement method based on denoising diffusion probabilistic model

Abstract

Underwater images often suffer from severe distortion, which seriously affects the image quality and the application. Current underwater image enhancement methods have poor generalization capability and cannot be adapted to all types of underwater images. In recent years, the diffusion model based on the denoising diffusion probabilistic model (DDPM) has achieved excellent results in various fields of computer vision. Inspired by the DDPM, an underwater image enhancement method based on the DDPM (UW-DDPM) was proposed in this paper. The UW-DDPM trained on paired datasets and utilized two U-Net networks to complete image denoising as well as image distribution transformation, which effectively improved the quality of underwater images. By testing on real underwater image datasets, UW-DDPM achieved better improvement in visual effects and evaluation metrics than the existing model.