Manuscript received July 18, 2024; revised August 21, 2024; accepted September 23, 2024, published May 19, 2025.

Abstract—Underwater vision is crucial for Autonomous Underwater Vehicles (AUVs), and enhancing degraded underwater images in real-time on a resource-constrained AUV is a key challenge due to factors like light absorption and scattering, or the sufficient model computational complexity to resolve such factors. Traditional image enhancement techniques lack adaptability to varying underwater conditions, while learning-based methods, particularly those using Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), offer more robust solutions but face limitations such as inadequate enhancement, unstable training, or mode collapse. Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a state-of-the-art approach in image-to-image tasks but require intensive computational complexity to achieve the desired Underwater Image Enhancement (UIE) using the recent Underwater DDPM (UW-DDPM) solution. To address these challenges, this paper introduces UW-DiffPhys, a novel physical-based and diffusion-based UIE approach. UW-DiffPhys combines light-computation physical-based UIE network components with a denoising U-Net to replace the computationally intensive distribution transformation U-Net in the existing UW-DDPM framework, reducing complexity while maintaining performance. Additionally, the Denoising Diffusion Implicit Model (DDIM) is employed to accelerate the inference process through non-Markovian sampling. Experimental results demonstrate that UW-DiffPhys achieved a substantial reduction in computational complexity and inference time compared to UW-DDPM, with competitive performance in key metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Underwater Color Image Quality Evaluation (UCIQE), and an improvement in the overall Underwater Image Quality Measure (UIQM) metric. The implementation code can be found at the following repository: https://github.com/bachzz/UW-DiffPhys

Keywords—Underwater Image Enhancement (UIE), Conditional Denoising Diffusion Probabilistic Model (DDPM), underwater physical image formation model

Cite: Nguyen Gia Bach, Chanh Minh Tran, Eiji Kamioka, and Phan Xuan Tan, "Underwater Image Enhancement with Physical-Based Denoising Diffusion Implicit Models," Journal of Image and Graphics, Vol. 13, No. 3, pp. 213-230, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.