Learning a Physical-Aware Diffusion Model Based on Transformer for Underwater Image Enhancement

Underwater visuals undergo various complex degra-dations, inevitably influencing the efficiency of underwater vision tasks. Recently, diffusion models were employed to underwater image enhancement (UIE) tasks, and gained the best performance. However, these methods fail to consider the physical properties and underwater imaging mechanisms in the diffusion process, limiting information completion capacity of diffusion models. In this paper, we introduce a novel UIE framework, named PA-Diff, designed to exploit physical knowledge to guide the diffusion process. PA-Diff consists of the Physics Prior Generation (PPG) branch, the Implicit Neural Reconstruction (INR) branch, and the Physics-aware Diffusion…

• NN
  National Natural Science Foundation of China

  Awards: 62371232, 62276138, Grant No. 62276138, Grant No. 62371232