EUVIMEDEUVIMED entdecken
Crossref

A Zero-Shot Network for Low-Light Image Enhancement With Brightness-Aware Representation and Semantic-Consistency Guidance

Huihong Huang, Zhida Ren, Xiaowen Shi, Gaowei Wu, Yongqiang Tang, Wensheng Zhang

IEEE Signal Processing Letters · 2026 · 33 · 2864-2868

DOI: 10.1109/lsp.2026.3695004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Huihong Huang und 5 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China, Special Project of Joint Funding for Municipal, University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-light image enhancement aims to restore visibility, contrast, and semantic fidelity to images captured under poor illumination, which often suffer from uneven lighting, detail loss, and noise. Most existing deep learning methods usually rely on paired datasets, which limits their generalization ability. To overcome these limitations, a new zero-shot low-light enhancement network, termed BRSGNet, is introduced to improve brightness-aware representation and enhance semantic consistency. Specifically, a Brightness-Aware Module (BAM) with multi-scale dilated convolution and spatial attention mechanisms is designed to improve illumination estimation while preserving global-local details. Then, a Semantic-Aware Network (SANet) incorporating a Semantic Feature Consistency Loss (SFC-Loss) is introduced to enforce semantic alignment between the enhanced and original images without requiring ground-truth references. Extensive experiments on three public benchmarks demonstrate that the proposed approach achieves competitive performance in terms of both visual quality and semantic consistency, showcasing strong generalization across diverse low-light conditions.

Förderung

  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China
  • Special Project of Joint Funding for Municipal, University
  • Guangzhou Basic Research Program
  • Science and Technology Projects in Guangzhou

Zitieren

APA

Huang, H., Ren, Z., Shi, X., Wu, G., Tang, Y., & Zhang, W. (2026). A Zero-Shot Network for Low-Light Image Enhancement With Brightness-Aware Representation and Semantic-Consistency Guidance. IEEE Signal Processing Letters, 33, 2864-2868. https://doi.org/10.1109/lsp.2026.3695004

Vancouver

Huang H, Ren Z, Shi X, Wu G, Tang Y, Zhang W. A Zero-Shot Network for Low-Light Image Enhancement With Brightness-Aware Representation and Semantic-Consistency Guidance. IEEE Signal Processing Letters. 2026;33:2864-2868. doi:10.1109/lsp.2026.3695004

BibTeX
@article{Huang2026,
  author = {Huang, Huihong and Ren, Zhida and Shi, Xiaowen and Wu, Gaowei and Tang, Yongqiang and Zhang, Wensheng},
  title = {A Zero-Shot Network for Low-Light Image Enhancement With Brightness-Aware Representation and Semantic-Consistency Guidance},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2864--2868},
  doi = {10.1109/lsp.2026.3695004}
}
Kostenlos starten →