EUVIMEDSkopri EUVIMED
Crossref

Low-light Image Enhancement via a Frequency-based Model with Structure and Texture Decomposition

Mingliang Zhou, Hongyue Leng, Bin Fang, Tao Xiang, Xuekai Wei, Weijia Jia

ACM Transactions on Multimedia Computing, Communications, and Applications · 2023-11-30 · 19 (6) · 1-23

DOI: 10.1145/3590965 ↗

At a glance

Journal article in ACM Transactions on Multimedia Computing, Communications, and Applications, published online on 2023-05-31. Written by Mingliang Zhou and 5 co-authors. Cited 43 times so far (Crossref); 55 references. Funded by: National Natural Science Foundation of China, General Program of National Natural Science Foundation of Chongqing, Fundamental Research Funds for the Central Universities.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

This article proposes a frequency-based structure and texture decomposition model in a Retinex-based framework for low-light image enhancement and noise suppression. First, we utilize the total variation-based noise estimation to decompose the observed image into low-frequency and high-frequency components. Second, we use a Gaussian kernel for noise suppression in the high-frequency layer. Third, we propose a frequency-based structure and texture decomposition method to achieve low-light enhancement. We extract texture and structure priors by using the high-frequency layer and a low-frequency layer, respectively. We present an optimization problem and solve it with the augmented Lagrange multiplier to generate a balance between structure and texture in the reflectance map. Our experimental results reveal that the proposed method can achieve superior performance in naturalness preservation and detail retention compared with state-of-the-art algorithms for low-light image enhancement. Our code is available on the following website. 1

Funding

  • National Natural Science Foundation of China
  • General Program of National Natural Science Foundation of Chongqing
  • Fundamental Research Funds for the Central Universities
  • Guangxi Key Laboratory of Cryptography and Information Security
  • Human Resources and Social Security Bureau project of Chongqing
  • Youth Project of Guizhou Education Department
  • University-Level Scientific Research Projects
  • Guizhou Provincial Education Department Young Science and Technology Talents Development Project

Cite

APA

Zhou, M., Leng, H., Fang, B., Xiang, T., Wei, X., & Jia, W. (2023). Low-light Image Enhancement via a Frequency-based Model with Structure and Texture Decomposition. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(6), 1-23. https://doi.org/10.1145/3590965

Vancouver

Zhou M, Leng H, Fang B, Xiang T, Wei X, Jia W. Low-light Image Enhancement via a Frequency-based Model with Structure and Texture Decomposition. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(6):1-23. doi:10.1145/3590965

BibTeX
@article{Zhou2023,
  author = {Zhou, Mingliang and Leng, Hongyue and Fang, Bin and Xiang, Tao and Wei, Xuekai and Jia, Weijia},
  title = {Low-light Image Enhancement via a Frequency-based Model with Structure and Texture Decomposition},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {6},
  pages = {1--23},
  doi = {10.1145/3590965}
}
Start for free →