EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DuBNet: residual-coupling-guided luminance—chrominance decoupling for low-light image enhancement

XunKai Yang, ZhiBin Zhang

Journal of King Saud University Computer and Information Sciences · 2026-11 · 38 (9)

DOI: 10.1007/s44443-026-01336-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 28.10.2026. Verfasst von XunKai Yang und 1 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Major Special Project of the Inner Mongolia Autonomous Region, the Inner Mongolia University independent project, the Inner Mongolia Natural Science Foundation project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-light image enhancement is challenging due to the strong entanglement between illumination degradation and sensor noise in RGB space, which often causes noise amplification and color distortion. We first present region-aware quantitative evidence that a luminance–chrominance transform provides a more separable degradation structure. On the LOLv2-Synthetic training set with 900 paired samples, YCrCb consistently reduces residual coupling across global, edge, dark, and texture regions, indicating that its decoupling advantage is not merely dominated by smooth background areas. Motivated by this analysis, we propose DuBNet, a luminance–chrominance decoupled framework with a luminance branch (Lum-Net) and a chrominance branch (Chr-Net), where Lum-Net incorporates a lightweight BrightnessEmbed module for exposure-aware adaptation. A fusion/refinement network (Fus-Net) then performs alternating feature-guided fusion using a compact Feature Guidance Block and an efficient attention residual block (ECACoordCAB) that combines ECA and Coordinate Attention for channel- and position-aware modulation. Experiments on LOLv1, LOLv2-Synthetic, LOLv2-Real, and FiveK show that DuBNet achieves competitive fidelity and perceptual quality against strong baselines. We further provide a reduced-complexity distilled variant, DuBNet-KD, to examine whether the proposed decoupled representation and fusion strategy remain effective under a smaller channel width.

Förderung

  • the Major Special Project of the Inner Mongolia Autonomous Region
  • the Inner Mongolia University independent project
  • the Inner Mongolia Natural Science Foundation project
  • the fund of supporting the reform and development of local universities

Zitieren

APA

Yang, X., & Zhang, Z. (2026). DuBNet: residual-coupling-guided luminance—chrominance decoupling for low-light image enhancement. Journal of King Saud University Computer and Information Sciences, 38(9). https://doi.org/10.1007/s44443-026-01336-8

Vancouver

Yang X, Zhang Z. DuBNet: residual-coupling-guided luminance—chrominance decoupling for low-light image enhancement. Journal of King Saud University Computer and Information Sciences. 2026;38(9). doi:10.1007/s44443-026-01336-8

BibTeX
@article{Yang2026,
  author = {Yang, XunKai and Zhang, ZhiBin},
  title = {DuBNet: residual-coupling-guided luminance—chrominance decoupling for low-light image enhancement},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {9},
  doi = {10.1007/s44443-026-01336-8}
}
Kostenlos starten →