This study addresses the issue of noise in low-light images, which is prevalent and significantly affects image quality. A convolutional neural network (CNN)-based low-light image denoising module is proposed to tackle the problem that existing single-stage CNN models cannot effectively remove noise in dark areas. The module extracts high and low-frequency features through constructed convolutional blocks and utilizes an attention module to better focus on key features. Additionally, a residual structure is employed to preserve image detail information. In terms of the loss function, this paper adopts the smooth L1 loss, which combines the robustness of L1 loss against outliers with the numerical stability of L2 loss. Experimental results show that the pre-trained model achieves a peak signal-to-noise ratio (PSNR) of 25.133 dB and a structural similarity (SSIM) of 0.913 on the LOL dataset, and a PSNR of 19.427 dB and an SSIM of 0.827 on the GladNet-Dataset for noise image recovery. This indicates that the proposed model is significantly effective in enhancing and denoising low-light images under non-uniform lighting conditions and performs well in denoising natural low-light scene images.

Xiaoting Niu, Guanghai Zheng. Research on Low-Light Image Enhancement Algorithm Based on Multi-Dimensional Attention. Academic Journal of Engineering and Technology Science (2025) Vol. 8, Issue 1: 56-64. https://doi.org/10.25236/AJETS.2025.080109.

[1] Y. Chen. Research on image denoising algorithm based on image filter optimization[D]. Southeast University, 2020.

[2] Z. F. Li, L. J. Gao, T. H. Zhang. Simulation of Multi-Feature Detail Recognition of ExposedImage Based on Filtering Algorithm[J]. Computer Simulation, 2023, 40 (12): 242-246+395.

[3] Y. C. Hou, H. Song. Remote Sensing Image Denoising Based on WaveletTransform and Improved DnCNN[J]. Computer Measurement & Control, 2022, 216-221. 

[4] T. Wang, C. Zhao, Z. Z. Chen, et al. Research on denoising method of high frequency ground wave radarocean echo spectrum based on DnCNN network[C]// Chinese Institute of Electronics. Proceedings of the 18th National Annual Conference on Radio Transmission. School of Electronic Information, Wuhan University, 2023: 4. 

[5] Wu Y, Xu Q, Zhang Z, et al. SAR Change Detection Algorithm Combined with FFDNet Spatial Denoising [J]. Journal of Environmental & Earth Sciences, 2023, 5 (2): 1-15.

[6] Y. Guo, R. L. Liang, R. M. Wang. Cross-Domain Adaptive Object Detection Based on CNN Image Enhancement in Foggy Conditions[J]. Computer Engineering and Applications, 2023, 59(16): 187-195.

[7] X. Z. Yang, W. Wu, T. S. Ren, et al. Complex Environment License Plate Recognition Algorithm Basedon Improved Image EnhancementandCNN[J]. Computer Science, 2024, 51 (S1): 574-580.

[8] W. T. Jiang, Y. F. Bu. Image Denoising Network Fusing with CNN and Transformer[J]. Computer Systems & Applications, 2024, 33(07): 39-51.

[9] C. G, C. L, J. G, et al. Zero-reference deep curve estimation for low-light image enhancement[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020, 1777-1786.

[10] W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang and J. Jiang, "URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement," 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 5891-5900.

[11] Saputra W V, Suciati N, Fatichah C. Low Light Image Enhancement in License Plate Recognition using URetinex-Net and TRBA[J]. Procedia Computer Science, 2024, 234404-411.

[12] S. Lin, F. Tang, W. Dong, X. Pan and C. Xu, "SMNet: Synchronous Multi-Scale Low Light Enhancement Network With Local and Global Concern," in IEEE Transactions on Multimedia, vol. 25, pp. 9506-9517, 2023. 

[13] Z. J. Zhu, G. Q. Zhao, Y. Gao, et al. Compressible Flowfields Machine Learning Inference Method for Airfoil Based on UNet[J]. Journal of Nanjing University of Aeronautics & Astronautic, 2024, 56(02): 253-263.

[14] Liu Y, Shao Z, Hoffmann N. Global attention mechanism: Retain information to enhance channel-spatial interactions[J]. arxiv preprint arxiv: 2112. 05561, 2021.

[15] Xu W, Wan Y. ELA: Efficient Local Attention for Deep Convolutional Neural Networks[J]. arXiv preprint arXiv: 2403. 01123, 2024.

[16] X. Liu, Y. J. Sun. Seismic Signal Denoising Based on Convolutional Neural Networkwith Residual and Attention Mechanism[J]. Journal of Jilin University( Earth Science Edition), 2023, 53(02): 609-621. 

[17] W. Wang, C. Wei, W. Yang and J. Liu, "GLADNet: Low-Light Enhancement Network with Global Awareness," 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), Xi'an, China, 2018, pp. 751-755.