UDBE: Unsupervised Diffusion-based Brightness Enhancement in Underwater Images

TL;DR

This paper presents UDBE, an unsupervised diffusion-based method for enhancing brightness in underwater images, effectively improving image quality without paired training data, and demonstrating robust results across multiple benchmarks.

Contribution

Introduces a novel unsupervised diffusion model for underwater brightness enhancement that maintains color fidelity and detail without requiring paired datasets.

Findings

Achieves high accuracy on UIEB, SUIM, and RUIE datasets.

Maintains color and detail without distortion.

Demonstrates robustness across multiple image quality metrics.

Abstract

Activities in underwater environments are paramount in several scenarios, which drives the continuous development of underwater image enhancement techniques. A major challenge in this domain is the depth at which images are captured, with increasing depth resulting in a darker environment. Most existing methods for underwater image enhancement focus on noise removal and color adjustment, with few works dedicated to brightness enhancement. This work introduces a novel unsupervised learning approach to underwater image enhancement using a diffusion model. Our method, called UDBE, is based on conditional diffusion to maintain the brightness details of the unpaired input images. The input image is combined with a color map and a Signal-Noise Relation map (SNR) to ensure stable training and prevent color distortion in the output images. The results demonstrate that our approach achieves an impressive accuracy rate in the datasets UIEB, SUIM and RUIE, well-established underwater image benchmarks. Additionally, the experiments validate the robustness of our approach, regarding the image quality metrics PSNR, SSIM, UIQM, and UISM, indicating the good performance of the brightness enhancement process. The source code is available here: https://github.com/gusanagy/UDBE.