Two Simple Unfolded Residual Networks for Single Image Dehazing

Bartomeu Garau, Joan Duran, Joan Duran, Catalina Sbert, Catalina Sbert

2025

Abstract

Haze is an environmental factor that impairs visibility for outdoor imaging systems, presenting challenges for computer vision tasks. In this paper, we propose two novel approaches that combine the classical dark channel prior with variational formulations to construct an energy functional for single-image dehazing. The proposed functional is minimized using a proximal gradient descent scheme, which is unfolded into two different networks: one built with residual blocks and the other with residual channel attention blocks. Both methods provide straightforward yet effective solutions for dehazing, achieving competitive results with simple and interpretable architectures.

Paper Citation

in Harvard Style

Garau B., Duran J. and Sbert C. (2025). Two Simple Unfolded Residual Networks for Single Image Dehazing. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 516-523. DOI: 10.5220/0013181400003912

in Bibtex Style

@conference{visapp25,
author={Bartomeu Garau and Joan Duran and Catalina Sbert},
title={Two Simple Unfolded Residual Networks for Single Image Dehazing},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={516-523},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013181400003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Two Simple Unfolded Residual Networks for Single Image Dehazing
SN - 978-989-758-728-3
AU - Garau B.
AU - Duran J.
AU - Sbert C.
PY - 2025
SP - 516
EP - 523
DO - 10.5220/0013181400003912
PB - SciTePress