Rethinking Zero-DCE for Low-Light Image Enhancement
Neural Processing Letters · 07.03.2024 · 56 (2)
DOI: 10.1007/s11063-024-11565-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Processing Letters, online erschienen am 07.03.2024. Verfasst von Aizhong Mi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Zero-Reference Deep Curve Estimation (Zero-DCE) is currently one of the most popular low-light image enhancement methods. Through extensive experimentation, we observe that: (i) the excellent performance of Zero-DCE depends on the training data with multiple exposure levels, (ii) it cannot effectively handle uneven light, extremely low light, or overexposed images in natural environments. Therefore, we propose an improved zero-reference dual-illumination deep curve estimation method for low-light image enhancement named Zero-DiDCE, which can enhance, suppress, or maintain light levels for images. The adaptive light enhancement curve was designed to handle images with different exposure levels. An iterator and amplitude controller are designed to control the curve enhancement intensity by calculating the gap between the input image and the optimal light level. Furthermore, instead of the DCE-Net in Zero-DCE only taking the input image as network input, our DiDCE-Net in Zero-DiDCE takes the input image and the inverted input image simultaneously as network input to ensure that the training set contains samples with multiple exposure levels. A piecewise non-reference loss function is designed to guide the training of DiDCE-Net from the perspective of information loss. Qualitative and quantitative experiments show that our method can handle images with different levels of exposure well and outperforms state-of-the-art methods. In addition, the proposed curve and iterator can be integrated into other methods to improve their enhancement effects. The code is available at https://github.com/Wenhui-Luo/Zero-DiDCE .
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Mi, A., Luo, W., Qiao, Y., & Huo, Z. (2024). Rethinking Zero-DCE for Low-Light Image Enhancement. Neural Processing Letters, 56(2). https://doi.org/10.1007/s11063-024-11565-5
Vancouver
Mi A, Luo W, Qiao Y, Huo Z. Rethinking Zero-DCE for Low-Light Image Enhancement. Neural Processing Letters. 2024;56(2). doi:10.1007/s11063-024-11565-5
BibTeX
@article{Mi2024,
author = {Mi, Aizhong and Luo, Wenhui and Qiao, Yingxu and Huo, Zhanqiang},
title = {Rethinking Zero-DCE for Low-Light Image Enhancement},
journal = {Neural Processing Letters},
year = {2024},
volume = {56},
number = {2},
doi = {10.1007/s11063-024-11565-5}
}
EUVIMED