EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Zero-Shot Low Light Image Enhancement Method Integrating Gating Mechanism

Junhao Tian, Jianwei Zhang iD

Sensors · 21.08.2023 · 23 (16) · 7306

DOI: 10.3390/s23167306 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.08.2023. Verfasst von Junhao Tian und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Sichuan University, Chengdu 610065, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key R&D Projects in Sichuan Province (Research on Intelligent Sensing Methods for Multimodal Targets in Complex Driving Environments).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Photographs taken under harsh ambient lighting can suffer from a number of image quality degradation phenomena due to insufficient exposure. These include reduced brightness, loss of transfer information, noise, and color distortion. In order to solve the above problems, researchers have proposed many deep learning-based methods to improve the illumination of images. However, most existing methods face the problem of difficulty in obtaining paired training data. In this context, a zero-reference image enhancement network for low light conditions is proposed in this paper. First, the improved Encoder-Decoder structure is used to extract image features to generate feature maps and generate the parameter matrix of the enhancement factor from the feature maps. Then, the enhancement curve is constructed using the parameter matrix. The image is iteratively enhanced using the enhancement curve and the enhancement parameters. Second, the unsupervised algorithm needs to design an image non-reference loss function in training. Four non-reference loss functions are introduced to train the parameter estimation network. Experiments on several datasets with only low-light images show that the proposed network has improved performance compared with other methods in NIQE, PIQE, and BRISQUE non-reference evaluation index, and ablation experiments are carried out for key parts, which proves the effectiveness of this method. At the same time, the performance data of the method on PC devices and mobile devices are investigated, and the experimental analysis is given. This proves the feasibility of the method in this paper in practical application.

Schlagwörter

Stichwörter der Autor:innen

lightweightlow light enhancementtransformerzero-shot

Autor:innen und Institutionen

  • School of Computer Science, Sichuan University, Chengdu 610065, China.

ORCID-Profile: Jianwei Zhang

Förderung

  • Key R&D Projects in Sichuan Province (Research on Intelligent Sensing Methods for Multimodal Targets in Complex Driving Environments)

Zitieren

APA

Tian, J., & Zhang, J. (2023). A Zero-Shot Low Light Image Enhancement Method Integrating Gating Mechanism. Sensors, 23(16), 7306. https://doi.org/10.3390/s23167306

Vancouver

Tian J, Zhang J. A Zero-Shot Low Light Image Enhancement Method Integrating Gating Mechanism. Sensors. 2023;23(16):7306. doi:10.3390/s23167306

BibTeX
@article{Tian2023,
  author = {Tian, Junhao and Zhang, Jianwei},
  title = {A Zero-Shot Low Light Image Enhancement Method Integrating Gating Mechanism},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {16},
  pages = {7306},
  doi = {10.3390/s23167306}
}
Kostenlos starten →