International Journal of Frontiers in Engineering Technology, 2025, 7(2); doi: 10.25236/IJFET.2025.070207.
Xiaoting Niu, Guanghai Zheng
School of Software, Dalian Jiaotong University, Dalian, China
This study addresses the prevalent issues of color bias and detail loss in low-light images, which significantly affect image quality. A low-light enhancement algorithm based on the combination of convolutional neural networks (CNN) and a dual-branch structure is proposed to address the problems of detail loss and color shift that existing single-stage CNN models cannot effectively handle. This module is trained with a contrastive regularization method on the basis of the dual-branch structure to ensure the consistency of detail distribution between the generated images and reference images. In terms of the loss function, a color loss function Lcolor is added to balance the low-light enhancement and color bias issues. Experimental results show that the pre-trained model achieved a peak signal-to-noise ratio (PSNR) of 22.133 dB and a structural similarity (SSIM) of 0.873 on the LOL dataset. This indicates that the proposed algorithm significantly improves the balance between image brightness and detail retention, and performs well in enhancing the brightness of natural low-light scene images.
CNN; Dual-Branch Structure; Contrastive Regularization; Low-Light Enhancement; Residual Learning
Xiaoting Niu, Guanghai Zheng. Research on Low-Light Image Enhancement Algorithm Based on Dual-Branch Structure. Intemational Journal of Frontiers in Engineering Technology(2025), Vol. 7, Issue 2: 46-55. https://doi.org/10.25236/IJFET.2025.070207.
[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. Li, C. Guo, and C. C. Loy, "Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, pp. 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, 234,404-411.
[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[J], vol. 25, pp. 9506-9517, 2023.
[13] Jongho L ,Man Y R .Dual-Branch Structured De-Striping Convolution Network Using Parametric Noise Model[J].IEEE ACCESS,2020,8, 155519-155528.
[14] Y. Chen, X. Dai, M. Liu, D. Chen, L. Yuan and Z. Liu, "Dynamic convolution: Attention over convolution kernels", Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 11030-11039, 2020.
[15] Z. Chen, Z. He, and M. Z. Lu, "DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention," IEEE Transactions on Image Processing, vol. 33, pp. 1002-1015, 2024.
[16] Liu, Q., Zhao, J., Cheng, C., Sheng, B., Ma, L.: Pointalcr: adversarial latent gan and contrastive regularization for point cloud completion. Vis. Comput. 38, 3341-3349,2022.