XYZ Unsupervised Network: A Robust Image Dehazing Approach

Percy Maldonado-Quispe, Helio Pedrini

2024

Abstract

In this work, we examine a major less-explored topic in image dehazing neural networks, specifically how to remove haze (natural phenomenon) in an unsupervised manner from a given image. By considering a hazy image as the entanglement of many “simpler” layers, such as a hazy-free image layer, transmission map layer, and atmospheric light layer, as shown in the atmospheric scattering model, we propose a method based on the concept of layer disentanglement. Our XYZ approach presents improvements in the SSIM and PSNR metrics, this being the combination of the XHOT, YOLY and ZID methods, in which the advantages of each of them are maintained. The main benefits of the proposed XYZ are twofold. First, since it is an unsupervised approach, no clean photos, including hazy-clear pairs, are used as the ground truth. In other words, it differs from the traditional paradigm of deep model training on a large dataset. The second is to consider haze issues as being composed of several layers.

Paper Citation

in Harvard Style

Maldonado-Quispe P. and Pedrini H. (2024). XYZ Unsupervised Network: A Robust Image Dehazing Approach. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 500-507. DOI: 10.5220/0012383400003660

in Bibtex Style

@conference{visapp24,
author={Percy Maldonado-Quispe and Helio Pedrini},
title={XYZ Unsupervised Network: A Robust Image Dehazing Approach},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={500-507},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012383400003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - XYZ Unsupervised Network: A Robust Image Dehazing Approach
SN - 978-989-758-679-8
AU - Maldonado-Quispe P.
AU - Pedrini H.
PY - 2024
SP - 500
EP - 507
DO - 10.5220/0012383400003660
PB - SciTePress