EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SCAUNet: Step-Size-Consistent ADMM Unfolding Network for Low-Light Image Enhancement

Xiaofang Li, Hongbiao Tian, Cui Fu

Mathematics · 09.06.2026 · 14 (12) · 2061

DOI: 10.3390/math14122061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 09.06.2026. Verfasst von Xiaofang Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xianyang Normal University, Shaanxi Provincial Education Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-light image enhancement aims to restore visually pleasing normal-light images from degraded low-light observations. Most existing methods handle luminance variation from the enhancement perspective. As a result, the degradation process from a normal-light image to a low-light observation is usually not explicitly characterized. In addition, degradation-oriented optimization is often computationally expensive due to repeated iterative updates. To address these issues, based on the alternating direction method of multipliers (ADMM), a degradation-oriented step-size-consistent unfolding network SCAUNet is proposed. Specifically, a low-light image is modeled as the element-wise product of a normal-light image and a luminance degradation operator, together with additive noise. Based on this formulation, low-light enhancement is converted into the joint estimation of the target image and the degradation operator. Then, a state-based one-step ADMM solver is developed, and a step-size consistency constraint is introduced to improve the reliability of one-step unfolding. Extensive experiments on LOL-v1 and LOL-v2 demonstrate the effectiveness of the proposed SCAUNet. Compared with existing state-of-the-art methods, SCAUNet yields better enhancement quality, especially in preserving image structures, correcting illumination, and suppressing artifacts. Strong generalization ability is also verified on four no-reference low-light datasets, and promising results are obtained on single-image exposure correction.

Förderung

  • Xianyang Normal University
  • Shaanxi Provincial Education Department

Zitieren

APA

Li, X., Tian, H., & Fu, C. (2026). SCAUNet: Step-Size-Consistent ADMM Unfolding Network for Low-Light Image Enhancement. Mathematics, 14(12), 2061. https://doi.org/10.3390/math14122061

Vancouver

Li X, Tian H, Fu C. SCAUNet: Step-Size-Consistent ADMM Unfolding Network for Low-Light Image Enhancement. Mathematics. 2026;14(12):2061. doi:10.3390/math14122061

BibTeX
@article{Li2026,
  author = {Li, Xiaofang and Tian, Hongbiao and Fu, Cui},
  title = {SCAUNet: Step-Size-Consistent ADMM Unfolding Network for Low-Light Image Enhancement},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {12},
  pages = {2061},
  doi = {10.3390/math14122061}
}
Kostenlos starten →