DiffUIE: Learning Latent Global Priors in Diffusion Models for Underwater Image Enhancement

作     者：Qing, Yuhao Liu, Si Wang, Hai Wang, Yueying 

作者机构：Shanghai Univ Sch Mechatron Engn & Automat Shanghai 200444 Peoples R China Beihang Univ Beijing 100083 Peoples R China Murdoch Univ Sch Energy Engn & Energy Murdoch WA 6150 Australia Murdoch Univ Adv Robot & Autonomous Syst Lab Murdoch WA 6150 Australia 

出 版 物：《IEEE TRANSACTIONS ON MULTIMEDIA》 (IEEE Trans Multimedia)

年 卷 期：2025年第27卷

页      面：2516-2529页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Key R&D Program of China [2023YFB4707000] National Natural Science Foundation of China [62122046, U24A20279, 62473243] Shanghai Commission of Science and Technology, China 

主　　题：Image color analysis Image enhancement Diffusion models Training Distortion Colored noise Noise Noise reduction Degradation Imaging Underwater image enhancement diffusion model global feature prior degenerate representation stable sampling 

摘      要：Underwater imagery often suffers from light attenuation and color distortion, resulting in images with low contrast and blurriness. Enhancing these images is crucial yet challenging due to the complex degradation and noise inherent in underwater environments. In this study, we introduce a novel diffusion model, termed Underwater Image Enhancement(UIE) Diffusion, which leverages a global feature prior for effective underwater image enhancement. To our knowledge, this is the inaugural application of a diffusion model to the task of underwater image enhancement, setting a new benchmark in performance. Our approach begins with the introduction of a global feature prior to augment the diffusion model, mitigating the impact of noise and distortion during training. We then incorporate an underwater image degradation model to facilitate the learning of mappings between high-quality and degraded underwater images. To address over-enhancement caused by high-frequency components, we employ scaling factors to modulate the influence of frequency features during diffusion. Additionally, we enhance the model s stability during inference by integrating a backward diffusion process into its training. Comprehensive evaluations on multiple public datasets demonstrate that UIE Diffusion surpasses existing state-of-the-art methods in both subjective outcomes and objective assessments.