Combining Total Variation and Nonlocal Variational Models for Low-Light Image Enhancement

Daniel Torres, Catalina Sbert, Joan Duran

2024

Abstract

Images captured under low-light conditions impose significant limitations on the performance of computer vision applications. Therefore, improving their quality by discounting the effects of the illumination is crucial. In this paper, we present a low-light image enhancement method based on the Retinex theory. Our approach estimates illumination and reflectance in two steps. First, the illumination is obtained as the minimizer of an energy functional involving total variation regularization, which favours piecewise smooth solutions. Next, the reflectance component is computed as the minimizer of an energy functional involving contrast-invariant nonlocal regularization and a fidelity term preserving the largest gradients of the input image.

Paper Citation

in Harvard Style

Torres D., Sbert C. and Duran J. (2024). Combining Total Variation and Nonlocal Variational Models for Low-Light Image Enhancement. 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 508-515. DOI: 10.5220/0012386300003660

in Bibtex Style

@conference{visapp24,
author={Daniel Torres and Catalina Sbert and Joan Duran},
title={Combining Total Variation and Nonlocal Variational Models for Low-Light Image Enhancement},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={508-515},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012386300003660},
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 - Combining Total Variation and Nonlocal Variational Models for Low-Light Image Enhancement
SN - 978-989-758-679-8
AU - Torres D.
AU - Sbert C.
AU - Duran J.
PY - 2024
SP - 508
EP - 515
DO - 10.5220/0012386300003660
PB - SciTePress