Variational Retinex Model with Illumination Guidance and Fractional Derivative for Low-Light Enhancement
Photonics · 08.07.2026 · 13 (7) · 657
DOI: 10.3390/photonics13070657 ↗Kurz gefasst
Fachartikel in der Zeitschrift Photonics, online erschienen am 08.07.2026. Verfasst von Minhan Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shaanxi Provincial Natural Science Foundation.
Abstract (Originalsprache)
Low-light enhancement is a crucial task in computer vision; it can improve either the subjective experience of viewers or the usability of computer vision systems designed for normal-light images. In this paper, a variational Retinex model in the image domain is developed for low-light enhancement, which infuses classical/fractional differentiation of the input image into the illumination/reflectance component by means of a structure/texture-aware map (SAM/TAM). Firstly, the SAM (TAM) is generated by the inverse square of classical (fractional) differentiation of the input image. Secondly, the regularization term of illumination (reflectance) is defined by utilizing the SAM (TAM) as a weighted matrix, and an illumination guidance term is incorporated into the objective function. The illumination guidance term encourages the estimated illumination to encompass more structural information by penalizing deviation of illumination from the illumination pre-estimated by a dark channel prior to a guided image filtering. Finally, an alternative algorithm is employed to solve the minimization problem involved in the model. The performance of the proposed method is evaluated on three datasets for low-light enhancement and compared with eight state-of-the-art Retinex methods, qualitatively and quantitatively. Evaluation results show that the proposed method generally achieves higher performance in terms of low-light enhancement.
Förderung
- Shaanxi Provincial Natural Science Foundation
Zitieren
APA
Yang, M., Liu, Z., Zhan, G., & Zhong, Q. (2026). Variational Retinex Model with Illumination Guidance and Fractional Derivative for Low-Light Enhancement. Photonics, 13(7), 657. https://doi.org/10.3390/photonics13070657
Vancouver
Yang M, Liu Z, Zhan G, Zhong Q. Variational Retinex Model with Illumination Guidance and Fractional Derivative for Low-Light Enhancement. Photonics. 2026;13(7):657. doi:10.3390/photonics13070657
BibTeX
@article{Yang2026,
author = {Yang, Minhan and Liu, Zinan and Zhan, Guoqi and Zhong, Qin},
title = {Variational Retinex Model with Illumination Guidance and Fractional Derivative for Low-Light Enhancement},
journal = {Photonics},
year = {2026},
volume = {13},
number = {7},
pages = {657},
doi = {10.3390/photonics13070657}
}
EUVIMED