An Attention-Enhanced Network with Joint Dehazing and Retinex-Based Enhancement for Underwater Images

TL;DR

This paper introduces a three-stage neural network that enhances underwater images by combining physical modeling, Retinex-based enhancement, and attention mechanisms, achieving state-of-the-art results.

Contribution

It proposes a novel ADR network extending the underwater image formation model with attention and Retinex techniques for improved image quality.

Findings

Demonstrates competitive performance on UIEB and UFO-120 datasets.

Outperforms existing methods in underwater image enhancement.

Effectively combines physical modeling with deep learning techniques.

Abstract

Underwater images suffer from severe wavelength-dependent light absorption and scattering, and turbidity due to suspended particles, degrading visual quality for applications in autonomous underwater vehicles (AUVs), marine biology, archaeology, and offshore infrastructure inspection. Classical IFM inadequately capture nonlinear underwater light behavior, while purely data-driven methods lack physical interpretability. This paper proposes a three-stage network named ADR, that extends the underwater image formation model with additional terms to perform underwater dehazing, followed by Retinex-based enhancement and attention-enabled U-Net++ refinement. Experiments on UIEB and UFO-120 benchmark datasets demonstrate competitive performance with state-of-the-art methods.