EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DADNet: Dual-Branch Low-Light Image Enhancement Network Based on Attention Mechanism and Dark Channel Prior

Lingyun Wang, Minli Tang, Hua Li, Feiyan Yang, Ming Yuan

Symmetry · 26.03.2026 · 18 (4) · 564

DOI: 10.3390/sym18040564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 26.03.2026. Verfasst von Lingyun Wang und 4 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foundation Research Project of Kaili University https://ror.org/02hzqbc55, Guizhou Provincial Science and Technology Projects, Science and Technology Innovation Talent Team Project of Data Science and Computing Intelligence of Guizhou Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Images captured in low-light conditions often have poor visibility, low contrast, and color distortion due to uneven lighting. Most existing enhancement methods often suffer from unstable brightness recovery and color cast, which affect both visual quality and performance of advanced vision tasks. To address those issues, we propose DADNet, a dual-branch network with an attention mechanism and dark channel prior containing an Illumination Enhancement Module (IEM) and Color Transformation Module (CTM). The IEM extracts multi-scale features and improves lighting based on the dark channel prior, while the CTM employs the attention mechanism to handle color features and adjust saturation adaptively. Experimental results on three datasets show that DADNet performs well in both qualitative and quantitative evaluations. It effectively preserves image structure and texture details while achieving a good balance between overall brightness and color quality.

Förderung

  • Foundation Research Project of Kaili University https://ror.org/02hzqbc55
  • Guizhou Provincial Science and Technology Projects
  • Science and Technology Innovation Talent Team Project of Data Science and Computing Intelligence of Guizhou Province
  • Scientific Research Platform (Key Laboratory) Project of Kaili University https://ror.org/02hzqbc55
  • Big Data and Pattern Recognition Research Team Project of Kaili University https://ror.org/02hzqbc55
  • Specialized Fund for the Doctoral of Kaili University https://ror.org/02hzqbc55
  • Basic Research Program of Qiandongnan Miao and Dong Autonomous Prefecture

Zitieren

APA

Wang, L., Tang, M., Li, H., Yang, F., & Yuan, M. (2026). DADNet: Dual-Branch Low-Light Image Enhancement Network Based on Attention Mechanism and Dark Channel Prior. Symmetry, 18(4), 564. https://doi.org/10.3390/sym18040564

Vancouver

Wang L, Tang M, Li H, Yang F, Yuan M. DADNet: Dual-Branch Low-Light Image Enhancement Network Based on Attention Mechanism and Dark Channel Prior. Symmetry. 2026;18(4):564. doi:10.3390/sym18040564

BibTeX
@article{Wang2026,
  author = {Wang, Lingyun and Tang, Minli and Li, Hua and Yang, Feiyan and Yuan, Ming},
  title = {DADNet: Dual-Branch Low-Light Image Enhancement Network Based on Attention Mechanism and Dark Channel Prior},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {4},
  pages = {564},
  doi = {10.3390/sym18040564}
}
Kostenlos starten →