Low-Light Image Enhancement by Combining Transformer and Convolutional Neural Network

Nianzeng Yuan, Xingyun Zhao, Bangyong Sun (), Wenjia Han, Jiahai Tan, Tao Duan and Xiaomei Gao
Additional contact information
Nianzeng Yuan: School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
Xingyun Zhao: School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
Bangyong Sun: School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
Wenjia Han: Key Laboratory of Pulp and Paper Science & Technology of Ministry of Education, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China
Jiahai Tan: State Key Laboratory of Transient Optics and Photonics, Chinese Academy of Sciences, Xi’an 710119, China
Tao Duan: State Key Laboratory of Transient Optics and Photonics, Chinese Academy of Sciences, Xi’an 710119, China
Xiaomei Gao: Xi’an Mapping and Printing of China National Administration of Coal Geology, Xi’an 710199, China

Mathematics, 2023, vol. 11, issue 7, 1-14

Abstract: Within low-light imaging environment, the insufficient reflected light from objects often results in unsatisfactory images with degradations of low contrast, noise artifacts, or color distortion. The captured low-light images usually lead to poor visual perception quality for color deficient or normal observers. To address the above problems, we propose an end-to-end low-light image enhancement network by combining transformer and CNN (convolutional neural network) to restore the normal light images. Specifically, the proposed enhancement network is designed into a U-shape structure with several functional fusion blocks. Each fusion block includes a transformer stem and a CNN stem, and those two stems collaborate to accurately extract the local and global features. In this way, the transformer stem is responsible for efficiently learning global semantic information and capturing long-term dependencies, while the CNN stem is good at learning local features and focusing on detailed features. Thus, the proposed enhancement network can accurately capture the comprehensive semantic information of low-light images, which significantly contribute to recover normal light images. The proposed method is compared with the current popular algorithms quantitatively and qualitatively. Subjectively, our method significantly improves the image brightness, suppresses the image noise, and maintains the texture details and color information. For objective metrics such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM), image perceptual similarity (LPIPS), DeltaE, and NIQE, our method improves the optimal values by 1.73 dB, 0.05, 0.043, 0.7939, and 0.6906, respectively, compared with other methods. The experimental results show that our proposed method can effectively solve the problems of underexposure, noise interference, and color inconsistency in micro-optical images, and has certain application value.

Keywords: image processing; deep learning; low-light image enhancement; self-attention mechanism (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/7/1657/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/7/1657/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:7:p:1657-:d:1111484

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().