Efficient Gamma-Based Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
Applied Sciences · 30.06.2025 · 15 (13) · 7382
DOI: 10.3390/app15137382 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 30.06.2025. Verfasst von Huitao Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China.
Abstract (Originalsprache)
In recent years, the continuous advancement of deep learning technology and its integration into the domain of low-light image enhancement have led to a steady improvement in enhancement effects. However, this progress has been accompanied by an increase in model complexity, imposing significant constraints on applications that demand high real-time performance. To address this challenge, inspired by the state-of-the-art Zero-DCE approach, we introduce a novel method that transforms the low-light image enhancement task into a curve estimation task tailored to each individual image, utilizing a lightweight shallow neural network. Specifically, we first design a novel curve formula based on Gamma correction, which we call the Gamma-based light-enhancement (GLE) curve. This curve enables outstanding performance in the enhancement task by directly mapping the input low-light image to the enhanced output at the pixel level, thereby eliminating the need for multiple iterative mappings as required in the Zero-DCE algorithm. As a result, our approach significantly improves inference speed. Additionally, we employ a lightweight network architecture to minimize computational complexity and introduce a novel global channel attention (GCA) module to enhance the nonlinear mapping capability of the neural network. The GCA module assigns distinct weights to each channel, allowing the network to focus more on critical features. Consequently, it enhances the effectiveness of low-light image enhancement while incurring a minimal computational cost. Finally, our method is trained using a set of zero-reference loss functions, akin to the Zero-DCE approach, without relying on paired or unpaired data. This ensures the practicality and applicability of our proposed method. The experimental results of both quantitative and qualitative comparisons demonstrate that, despite its lightweight design, the images enhanced using our method not only exhibit perceptual quality, authenticity, and contrast comparable to those of mainstream state-of-the-art (SOTA) methods but in some cases even surpass them. Furthermore, our model demonstrates very fast inference speed, making it suitable for real-time inference in resource-constrained or mobile environments, with broad application prospects.
Förderung
- Natural Science Foundation of China
Zitieren
APA
Zhao, H., Xu, S., Peng, L., Hu, H., & Jiang, S. (2025). Efficient Gamma-Based Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. Applied Sciences, 15(13), 7382. https://doi.org/10.3390/app15137382
Vancouver
Zhao H, Xu S, Peng L, Hu H, Jiang S. Efficient Gamma-Based Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. Applied Sciences. 2025;15(13):7382. doi:10.3390/app15137382
BibTeX
@article{Zhao2025,
author = {Zhao, Huitao and Xu, Shaoping and Peng, Liang and Hu, Hanyang and Jiang, Shunliang},
title = {Efficient Gamma-Based Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {13},
pages = {7382},
doi = {10.3390/app15137382}
}
EUVIMED