EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Boosting Diffusion Networks with Deep External Context-Aware Encoders for Low-Light Image Enhancement

Pengliang Tang iD, Yu Wang iD, Aidong Men iD

Sensors · 27.11.2025 · 25 (23) · 7232

DOI: 10.3390/s25237232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.11.2025. Verfasst von Pengliang Tang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-light image enhancement (LLIE) requires modeling spatially extensive and interdependent degradations across large pixel regions, while directly equipping diffusion-based LLIE with heavy global modules inside the iterative denoising backbone leads to prohibitive computational overhead. To enhance long-range context modeling without inflating the per-step cost of diffusion, we propose ECA-Diff, a diffusion framework augmented with a deep External Context-Aware Encoder (ECAE). A latent-space context network built with hybrid Transformer–Convolution blocks extracts holistic cues from the input, generates multi-scale context features once, and injects them into the diffusion backbone as lightweight conditional guidance across all sampling steps. In addition, a CIELAB-space Luminance-Adaptive Chromaticity Loss regularizes conditional diffusion training and mitigates the cool color cast frequently observed in low-luminance regions. Experiments on paired and unpaired benchmarks show that ECA-Diff consistently outperforms recent state-of-the-art LLIE methods in both full-reference (PSNR/SSIM/LPIPS) and no-reference (NIQE/BRISQUE) metrics, with the external context path introducing only modest overhead relative to the baseline diffusion backbone. These results indicate that decoupling global context estimation from the iterative denoising process is an effective way to boost diffusion-based LLIE and provides a general compute-once conditioning paradigm for low-level image restoration.

Schlagwörter

Stichwörter der Autor:innen

CIELAB spacecontext modelingdiffusion modelshybrid Transformer–Convolution blockslow-light image enhancement

Autor:innen und Institutionen

  • School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China.

ORCID-Profile: Pengliang Tang, Yu Wang, Aidong Men

Zitieren

APA

Tang, P., Wang, Y., & Men, A. (2025). Boosting Diffusion Networks with Deep External Context-Aware Encoders for Low-Light Image Enhancement. Sensors, 25(23), 7232. https://doi.org/10.3390/s25237232

Vancouver

Tang P, Wang Y, Men A. Boosting Diffusion Networks with Deep External Context-Aware Encoders for Low-Light Image Enhancement. Sensors. 2025;25(23):7232. doi:10.3390/s25237232

BibTeX
@article{Tang2025,
  author = {Tang, Pengliang and Wang, Yu and Men, Aidong},
  title = {Boosting Diffusion Networks with Deep External Context-Aware Encoders for Low-Light Image Enhancement},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {23},
  pages = {7232},
  doi = {10.3390/s25237232}
}
Kostenlos starten →