Low-Light Image Enhancement Algorithm Based on Deep Learning and Retinex Theory
Source abstract
Abstract
To address the challenges of low-light images, such as low brightness, poor contrast, and high noise, a network model based on deep learning and Retinex theory is proposed. The model consists of three modules: image decomposition, illumination enhancement, and color restoration. In the image decomposition module, dilated convolutions and residual connections are employed to mitigate the issue of detail loss during the decomposition process. The illumination enhancement module utilizes a set of mapping curves to enhance the illumination map. The color restoration module employs a weighted fusion of a 3D lookup table (3DLUT) to mitigate color distortion in the images. The experimental results demonstrate that the proposed algorithm effectively improves the brightness and contrast of low-light images while addressing the issues of detail loss and color distortion. Compared to other algorithms, it achieves better subjective and objective evaluations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Advanced Image Fusion Techniques · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
References (27)
Show source-provided references
1. Pan, X., Li, C., Pan, Z., Yan, J., Tang, S., and Yin, X. (2022). Low-Light Image Enhancement Method Based on Retinex Theory by Improving Illumination Map. Appl. Sci., 12.10.3390/app12105257 ↗
2. Adaptive histogram equalization and its variations10.1016/S0734-189X(87)80186-X ↗
3. Dong, X., Pang, Y., and Wen, J. (2010). ACM SIGGRAPH 2010 Posters, Association for Computing Machinery.
4. Chandana, D.S., Chigurupati, K., Srikrishna, A., and Venkateswarlu, B. (2019, January 5–6). An optimal image dehazing technique using dark channel prior. Proceedings of the 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kannur, India.10.1109/ICICICT46008.2019.8993313 ↗
5. The retinex theory of color vision10.1038/scientificamerican1277-108 ↗
6. Properties and performance of a center/surround retinex10.1109/83.557356 ↗
7. Rahman, Z.U., Jobson, D.J., and Woodell, G.A. (1996, January 19). Multi-scale retinex for color image enhancement. Proceedings of the 3rd IEEE International Conference on Image Processing, Lausanne, Switzerland.10.1109/ICIP.1996.560995 ↗
8. A multiscale retinex for bridging the gap between color images and the human observation of scenes10.1109/83.597272 ↗
9. Low-light image enhancement via poisson noise aware retinex model10.1109/LSP.2021.3096160 ↗
10. LLNet: A deep autoencoder approach to natural low-light image enhancement10.1016/j.patcog.2016.06.008 ↗
11. Shen, L., Yue, Z., Feng, F., Chen, Q., Liu, S., and Ma, J. (2017). Msr-net: Low-light image enhancement using deep convolutional network. arXiv.
12. Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv.
13. Zhang, Y., Zhang, J., and Guo, X. (2019, January 21–25). Kindling the darkness: A practical low-light image enhancer. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.10.1145/3343031.3350926 ↗
14. Enlightengan: Deep light enhancement without paired supervision10.1109/TIP.2021.3051462 ↗
15. Guo, C., Li, C., Guo, J., Loy, C.C., Hou, J., Kwong, S., and Cong, R. (2020, January 13–19). Zero-reference deep curve estimation for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00185 ↗
16. Yang, W., Wang, S., Fang, Y., Wang, Y., and Liu, J. (2020, January 13–19). From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00313 ↗
17. Unsupervised low-light image enhancement using bright channel prior10.1109/LSP.2020.2965824 ↗
18. Zhang, Z., Zheng, H., Hong, R., Xu, M., Yan, S., and Wang, M. (2022, January 18–24). Deep color consistent network for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00194 ↗
19. Wu, W., Weng, J., Zhang, P., Wang, X., Yang, W., and Jiang, J. (2022, January 18–24). Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00581 ↗
20. D2bgan: A dark to bright image conversion model for quality enhancement and analysis tasks without paired supervision10.1109/ACCESS.2022.3178698 ↗
21. LACN: A lightweight attention-guided ConvNeXt network for low-light image enhancement10.1016/j.engappai.2022.105632 ↗
22. Zuiderveld, K. (1994). Graphics Gems, Academic Press.
23. LR3M: Robust low-light enhancement via low-rank regularized retinex model10.1109/TIP.2020.2984098 ↗
24. Wang, R., Zhang, Q., Fu, C.W., Shen, X., Zheng, W.S., and Jia, J. (2019, January 15–20). Underexposed photo enhancement using deep illumination estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00701 ↗
25. Learning to enhance low-light image via zero-reference deep curve estimation
26. LIME: Low-light image enhancement via illumination map estimation10.1109/TIP.2016.2639450 ↗
27. Zhang, Q., Yuan, G., Xiao, C., Zhu, L., and Zheng, W.S. (2018, January 22–26). High-quality exposure correction of underexposed photos. Proceedings of the 26th ACM International Conference on Multimedia, Seoul, Republic of Korea.10.1145/3240508.3240595 ↗