Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement

arXiv:2403.01497v1 Announce Type: new
Abstract: Underwater visuals undergo various complex degradations, inevitably influencing the efficiency of underwater vision tasks. Recently, diffusion models were employed to underwater image enhancement (UIE) tasks, and gained SOTA 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 exploiting the knowledge of physics to guide the diffusion …

abstract arxiv cs.cv diffusion diffusion model diffusion models efficiency image imaging performance sota tasks transformer type underwater vision visuals