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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ray, Sahana, Debnath, Bibhabasu, Ghosh, Sanjay
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910221356498944
author Ray, Sahana
Debnath, Bibhabasu
Ghosh, Sanjay
author_facet Ray, Sahana
Debnath, Bibhabasu
Ghosh, Sanjay
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14677
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Attention-Enhanced Network with Joint Dehazing and Retinex-Based Enhancement for Underwater Images
Ray, Sahana
Debnath, Bibhabasu
Ghosh, Sanjay
Image and Video Processing
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.
title An Attention-Enhanced Network with Joint Dehazing and Retinex-Based Enhancement for Underwater Images
topic Image and Video Processing
url https://arxiv.org/abs/2605.14677