Analysis of Trends and Development of Low-Light Image Enhancement Methods in Computer Vision

Ani Sanirah; Sri  Rahayu; Ade Bastian

doi:10.59934/jaiea.v5i3.2372

Authors

Ani Sanirah Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia
Sri Rahayu Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia
Ade Bastian Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

DOI:

https://doi.org/10.59934/jaiea.v5i3.2372

Keywords:

Computer vision, Deep learning, Low-light image enhancement, Systematic literature review, Zero-reference learning

Abstract

This study investigates the development of Low-Light Image Enhancement (LLIE) methods in the field of computer vision using a Systematic Literature Review (SLR) approach. The review was conducted on 56 scientific articles selected from a total of 604 papers entirely sourced from the Scopus database based on the PRISMA 2020 guidelines. The results indicate that LLIE research has evolved from traditional methods, such as histogram equalization and Retinex, toward deep learning-based approaches including CNN, GAN, Transformer, and diffusion models. Modern methods have demonstrated superior performance in improving image illumination, preserving details, and reducing noise. In addition, real-world datasets and zero-reference approaches are increasingly adopted to improve model generalization capability. However, challenges remain regarding computational complexity, detail preservation, and model performance under extreme low-light conditions. This study concludes that future LLIE research will focus on developing models that are more adaptive, efficient, lightweight, and robust for various computer vision applications.

Downloads

Download data is not yet available.

Author Biographies

Ani Sanirah, Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

Sri Rahayu, Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

Ade Bastian, Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

Program Studi Informatika, Fakultas Teknik, Universitas Majalengka, Indonesia

References

Y. Zhou, L. Xie, K. He, D. Xu, D. Tao, and X. Lin, “Low-light image enhancement for infrared and visible image fusion,” IET Image Process., vol. 17, no. 11, pp. 3216–3234, Sep. 2023, doi: 10.1049/ipr2.12857.

F. Tian, M. Wang, and X. Liu, “Low-Light Mine Image Enhancement Algorithm Based on Improved Retinex,” Applied Sciences (Switzerland), vol. 14, no. 5, Mar. 2024, doi: 10.3390/app14052213.

H. Hussain, P. S. Tamizharasan, and P. K. Yadav, “OptiRet-Net: An Optimized Low-Light Image Enhancement Technique for CV-Based Applications in Resource-Constrained Environments,” ACM Trans. Intell. Syst. Technol., vol. 15, no. 6, Dec. 2024, doi: 10.1145/3700136.

P. Ji, Z. Lv, and Z. Zhang, “A Retinex-Based Network for Low-Light Image Enhancement With Multi-Scale Denoising and Focal-Aware Reflections,” IET Image Process., vol. 19, no. 1, Jan. 2025, doi: 10.1049/ipr2.70059.

J. Chen, Z. Xiao, X. Qin, and D. Luo, “Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention,” Electronics (Switzerland), vol. 14, no. 11, Jun. 2025, doi: 10.3390/electronics14112212.

Y. Zhang et al., “Low-light image enhancement method based on retinex theory and dual-tree complex wavelet transform,” Journal of King Saud University - Computer and Information Sciences, vol. 37, no. 5, Jul. 2025, doi: 10.1007/s44443-025-00102-6.

Y. Jiang, J. Zhu, L. Li, and H. Ma, “A Joint Network for Low-Light Image Enhancement Based on Retinex,” Cognit. Comput., vol. 16, no. 6, pp. 3241–3259, Nov. 2024, doi: 10.1007/s12559-024-10347-4.

M. Abisado, “Brightness-Aware Generative Adversarial Network for Low-Light Image Enhancement.” [Online]. Available: www.ijacsa.thesai.org

S. Du, X. Qin, M. Zhao, J. Hu, L. Wang, and P. Li, “Non-Uniform Low-Light Stereo Image Enhancement Based on Transformer,” in ASIG 2024 - Proceedings of the 2nd Asia Symposium on Image and Graphics, Association for Computing Machinery, Inc, Apr. 2025, pp. 164–170. doi: 10.1145/3718441.3718477.

A. Rahmatulloh, E. Haerani, R. Gunawan, E. A. Firdaus, and G. F. Nugraha, “ALEX: Automated Low-Light Enhancement eXpert for Intelligent Security Systems Using Vision Transformer,” Cybernetics and Information Technologies, vol. 25, no. 4, pp. 145–165, Dec. 2025, doi: 10.2478/cait-2025-0038.

T. Wang, K. Zhang, T. Shen, W. Luo, B. Stenger, and T. Lu, “Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method,” 2023. [Online]. Available: https://github.com/TaoWangzj/LLFormer.

W. Lian, W. Lian, and Z. Luo, “Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement,” Apr. 2024, [Online]. Available: http://arxiv.org/abs/2404.09735

Q. An and L. Ma, “AFMNet: A Dual-Domain Collaborative Network with Frequency Prior Guidance for Low-Light Image Enhancement,” Entropy, vol. 27, no. 12, Dec. 2025, doi: 10.3390/e27121220.

Y. Lin et al., “AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement,” 2025. [Online]. Available: www.aaai.org

Y. Wu, G. Wu, and R. Liao, “EWRD: Entropy-Weighted Low-Light Image Enhancement via Reverse Diffusion Model,” International Journal of Intelligent Systems, vol. 2024, no. 1, 2024, doi: 10.1155/2024/4650233.

Y. Li et al., “Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines,” Complex and Intelligent Systems, vol. 11, no. 8, Aug. 2025, doi: 10.1007/s40747-025-01966-x.

S. Siringo Ringo, “Systematic Literature Review dengan Metode Prisma: Pembelajaran Berdiferensiasi pada Pendidikan Dasar,” Jurnal Didaktika Pendidikan Dasar, vol. 9, no. 1, pp. 209–226, Mar. 2025, doi: 10.26811/didaktika.v9i1.1760.

N. R. Haddaway, M. J. Page, C. C. Pritchard, and L. A. McGuinness, “PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis,” Campbell Systematic Reviews, vol. 18, no. 2, Jun. 2022, doi: 10.1002/cl2.1230.

H. In, J. Kweon, and C. Moon, “Squeeze-EnGAN: Memory Efficient and Unsupervised Low-Light Image Enhancement for Intelligent Vehicles,” Sensors, vol. 25, no. 6, Mar. 2025, doi: 10.3390/s25061825.

T. Zhang, P. Liu, M. Zhao, and H. Lv, “DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement,” in MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia, Association for Computing Machinery, Inc, Oct. 2024, pp. 7434–7443. doi: 10.1145/3664647.3681083.

W. Zou, H. Gao, W. Yang, and T. Liu, “Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement,” in MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia, Association for Computing Machinery, Inc, Oct. 2024, pp. 1534–1543. doi: 10.1145/3664647.3681580.

Y. Lin et al., “DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors,” 2025. [Online]. Available: www.aaai.org

Z. Wei, Y. Wang, K. Debattista, and V. Donzella, “Rethinking probabilistic learning for counterfactual low-light image enhancement in robust engineering vision systems,” Knowl. Based. Syst., vol. 340, May 2026, doi: 10.1016/j.knosys.2026.115666.

M. Liu, X. Li, and Y. Fang, “Low-Light Image Enhancement via Dual Information-Based Networks,” Electronics (Switzerland), vol. 13, no. 18, Sep. 2024, doi: 10.3390/electronics13183713.

Y. Jiang and S. Guo, “Low-Light Image Enhancement Algorithm Integrating Retinex Illumination Estimation and Multi-Attention,” IEEE Access, vol. 13, pp. 112805–112817, 2025, doi: 10.1109/ACCESS.2025.3583723.

F. Zhang, X. Liu, C. Gao, and N. Sang, “Color and Luminance Separated Enhancement for Low-Light Images with Brightness Guidance,” Sensors, vol. 24, no. 9, May 2024, doi: 10.3390/s24092711.

Z. Li, “Low light image enhancement algorithm based on edge and colour information,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Apr. 2024. doi: 10.1145/3663976.3663988.

Q. Li, B. Jiang, X. Bo, C. Yang, and X. Wu, “DANet: A Domain Alignment Network for Low-Light Image Enhancement,” Electronics (Switzerland), vol. 13, no. 15, Aug. 2024, doi: 10.3390/electronics13152954.

D. Torres, C. Sbert, and J. Duran, “Combining Total Variation and Nonlocal Variational Models for Low-Light Image Enhancement,” in Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications, Lda, 2024, pp. 508–515. doi: 10.5220/0012386300003660.

R. Weng, Y. Zhang, H. Wu, W. Wang, and D. Wang, “The Retinex enhancement algorithm for low-light intensity image based on improved illumination map,” IET Image Process., vol. 18, no. 12, pp. 3381–3392, Oct. 2024, doi: 10.1049/ipr2.13180.

R. Zaghloul and H. Hiary, “EnGMHE: Enhanced Geometric Mean Histogram Equalization for Low-Light Image Enhancement,” 2026. [Online]. Available: www.ijacsa.thesai.org

J. Wang, Y. Sun, and J. Yang, “Multi-Modular Network-Based Retinex Fusion Approach for Low-Light Image Enhancement,” Electronics (Switzerland), vol. 13, no. 11, Jun. 2024, doi: 10.3390/electronics13112040.

Z. Hu, O. Shkurat, K. Przystupa, O. Kochan, and M. Ivakhnenko, “Low-Light Image Enhancement Technology Based on Image Categorization, Processing and Retinex Deep Network,” International Journal of Image, Graphics and Signal Processing, vol. 16, no. 5, Oct. 2024, doi: 10.5815/ijigsp.2024.05.01.

Y. Chen, C. Wen, W. Liu, and W. He, “DBENet: Dual-Branch Brightness Enhancement Fusion Network for Low-Light Image Enhancement,” Electronics (Switzerland), vol. 12, no. 18, Sep. 2023, doi: 10.3390/electronics12183907.

X. Cao and J. Yu, “LLE-NET: A Low-Light Image Enhancement Algorithm Based on Curve Estimation,” Mathematics, vol. 12, no. 8, Apr. 2024, doi: 10.3390/math12081228.

Y. Li et al., “A Deep Retinex-Based Low-Light Enhancement Network Fusing Rich Intrinsic Prior Information,” ACM Transactions on Multimedia Computing, Communications and Applications, vol. 20, no. 11, Nov. 2024, doi: 10.1145/3689642.

M. Xue, Y. He, P. Xie, Z. He, and X. Feng, “LAE-GAN: a novel cloud-based Low-light Attention Enhancement Generative Adversarial Network for unpaired text images,” Journal of Cloud Computing, vol. 12, no. 1, Dec. 2023, doi: 10.1186/s13677-023-00533-4.

Y. Cai, X. Liu, H. Li, F. Lu, X. Gu, and K. Qin, “Research on Unsupervised Low-Light Railway Fastener Image Enhancement Method Based on Contrastive Learning GAN,” Sensors, vol. 24, no. 12, Jun. 2024, doi: 10.3390/s24123794.

Y. Zhou, X. Gao, J. Guo, G. Li, L. Wang, and J. Liu, “LUXFormer: Low-light image enhancement via joint spatial-frequency illumination modeling,” Journal of King Saud University - Computer and Information Sciences, vol. 37, no. 8, Oct. 2025, doi: 10.1007/s44443-025-00270-5.

H. Wang, H. Cui, J. Li, and Z. Hua, “HCTMIF: Hybrid CNN-Transformer Multi Information Fusion Network for Low Light Image Enhancement,” IET Image Process., vol. 19, no. 1, Jan. 2025, doi: 10.1049/ipr2.70127.

R. Zhou et al., “Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000. A Low-Light Image Enhancement Algorithm Incorporating Cross-Mixed Attention and Receptive Field Expansion Mechanism”, doi: 10.1109/ACCESS.2023.1120000.

“WMANet Wavelet-Based Multi-Scale Attention Network for Low-Light Image Enhancement”.

H. Zhou, J. Li, Y. Mao, L. Liu, and Y. Lu, “DFCNet: Dual-Stage Frequency-Domain Calibration Network for Low-Light Image Enhancement,” J. Imaging, vol. 11, no. 8, Aug. 2025, doi: 10.3390/jimaging11080253.

S. Zhang et al., “Towards Illumination-Guided Bilateral Grid Learning in Zero-Reference Low-Light Enhancement,” IEEE Access, 2026, doi: 10.1109/ACCESS.2026.3659099.

J. Zhang, H. Li, and Z. Huo, “Unsupervised Boosted Fusion Network for Single Low-Light Image Enhancement,” IEEE Access, vol. 12, pp. 179252–179264, 2024, doi: 10.1109/ACCESS.2024.3502654.

X. Wang, L. Huang, M. Li, C. Han, X. Liu, and T. Nie, “Fast, Zero-Reference Low-Light Image Enhancement with Camera Response Model,” Sensors, vol. 24, no. 15, Aug. 2024, doi: 10.3390/s24155019.

A. Mi, W. Luo, Y. Qiao, and Z. Huo, “Rethinking Zero-DCE for Low-Light Image Enhancement,” Neural Process. Lett., vol. 56, no. 2, Apr. 2024, doi: 10.1007/s11063-024-11565-5.

X. Gao, K. Zhao, L. Han, and J. Luo, “BézierCE: Low-Light Image Enhancement via Zero-Reference Bézier Curve Estimation,” Sensors, vol. 23, no. 23, Dec. 2023, doi: 10.3390/s23239593.

G. Yue et al., “SGNet: Style-Guided Network with Temporal Compensation for Unpaired Low-Light Colonoscopy Video Enhancement,” IEEE Transactions on Image Processing, 2025, doi: 10.1109/TIP.2025.3644172.

Z. Sun, S. Hu, H. Song, and P. Liang, “Learning Wasserstein Contrastive Color Histogram Representation for Low-Light Image Enhancement,” Mathematics, vol. 11, no. 19, Oct. 2023, doi: 10.3390/math11194194.

S. Ono, Y. Ogino, T. Toizumi, A. Ito, and M. Tsukada, “Recognition-Oriented Low-Light Image Enhancement Based on Global and Pixelwise Optimization,” in Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications, Lda, 2025, pp. 222–232. doi: 10.5220/0013316800003912.

N. Zheng, J. Huang, M. Zhou, Z. Yang, Q. Zhu, and F. Zhao, “Learning Semantic Degradation-Aware Guidance for Recognition-Driven Unsupervised Low-Light Image Enhancement,” 2023. [Online]. Available: www.aaai.org

H. Zhang, X. S. Zhang, K. F. Yang, Y. J. Li, and L. L. H. Chan, “Retina adaptation network for low-light image enhancement,” Pattern Recognit., vol. 172, Apr. 2026, doi: 10.1016/j.patcog.2025.112629.

N. Zhang, X. Han, C. Liu, R. Gang, S. Ma, and Y. Cao, “Joint Luminance Adjustment and Color Correction for Low-Light Image Enhancement Network,” Applied Sciences (Switzerland), vol. 14, no. 14, Jul. 2024, doi: 10.3390/app14146320.

M. Y. Kuo and S. De Wang, “GWNet: A Lightweight Model for Low-Light Image Enhancement Using Gamma Correction and Wavelet Transform,” in International Conference on Agents and Artificial Intelligence, Science and Technology Publications, Lda, 2025, pp. 264–274. doi: 10.5220/0013148800003890.

J.-C. Tang, W.-Y. Cheng, and D.-Y. Chen, “SOGKD-Lite: Lightweight Semantic Object-Guided Network for Efficient Low-Light Image Enhancement via Knowledge Distillation,” IEEE Access, pp. 1–1, Jan. 2026, doi: 10.1109/access.2026.3655389.

V. Frants, S. Agaian, K. Panetta, and A. Grigoryan, “QWR-Dec-Net: A Quaternion-Wavelet Retinex Framework for Low-Light Image Enhancement with Applications to Remote Sensing,” Information, vol. 17, no. 1, p. 89, Jan. 2026, doi: 10.3390/info17010089.

C. Shi et al., “RICNET: Retinex-Inspired Illumination Curve Estimation for Low-Light Enhancement in Industrial Welding Scenes,” Sensors, vol. 25, no. 16, Aug. 2025, doi: 10.3390/s25165192.