Abstract
Existing network-based techniques addressing low-light image enhancement are developed by using the complex network architectures. However, the performance is not ideal, and they cannot give a reasonable interpretation of the effects of each layer in the network. To settle these issues, we design a residual network to learn multi-scale Retinex for handling low-light image enhancement. To be concrete, inspired by multi-scale Retinex, we define a new residual-type multi-scale Retinex model to gradually remove the illumination generated by the convolutional procedure. Thanks to the progressive mechanism, we can build an intuitive and explicit relationship between our residual-type multi-scale Retinex model and residual network. This enables us can directly utilize the residual network to learn a residual-type multi-scale Retinex by integrating the data distribution. Precisely because of our transparent modeling procedure, we can recognize the effects of each layer in our learnable architecture. It is valuable for more effectively exploit the network layers to handle this task. Extensive analytical experiments are performed to verify the effectiveness of our proposed method. A series of evaluative experiments are conducted to illustrate our superiority against other state-of-the-art methods.
Supported by the National Natural Science Foundation of China (Nos. 61922019, 61733002, and 61672125), LiaoNing Revitalization Talents Program (XLYC1807088), and the Fundamental Research Funds for the Central Universities (DUT19TD19).
The first author is a student.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, C., Guo, J., Porikli, F., Pang, Y.: Lightennet: a convolutional neural network for weakly illuminated image enhancement. PRL 104, 15–22 (2018)
Jiang, Y., Gong, X., Liu, D., et al.: Enlightengan: deep light enhancement without paired supervision. arXiv preprint arXiv:1906.06972 (2019)
Wang, R., Zhang, Q., Fu, C.-W., Shen, X., Zheng, W.-S., Jia, J.: Underexposed photo enhancement using deep illumination estimation. In: CVPR, pp. 6849–6857 (2019)
Jobson, D.J., Rahman, Z., Woodell, G.A.: Properties and performance of a center/surround retinex. IEEE TIP 6(3), 451–462 (1997)
Rahman, Z., Jobson, D.J., Woodell, G.A.: Multi-scale retinex for color image enhancement. In: ICIP, pp.1003–1006 (1996)
Jobson, D.J., Rahman, Z., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE TIP 6(7), 965–976 (1997)
Xueyang, F., Liao, Y., Zeng, D., Huang, Y., Zhang, X.-P., Ding, X.: A probabilistic method for image enhancement with simultaneous illumination and reflectance estimation. IEEE TIP 24(12), 4965–4977 (2015)
Fu, X., Zeng, D., Huang, Y., Zhang, X.-P., Ding, X.: A weighted variational model for simultaneous reflectance and illumination estimation. In: CVPR, pp. 2782–2790 (2016)
Guo, X., Li, Y., Ling, H.: Lime: Low-light image enhancement via illumination map estimation. IEEE TIP 26(2), 982–993 (2017)
Cai, B., Xu, X., Guo, K., Jia, K., Hu, B., Tao, D.: A joint intrinsic-extrinsic prior model for retinex. In: ICCV, pp. 4000–4009 (2017)
Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing low-light image enhancement via robust retinex model. IEEE TIP 27(6), 2828–2841 (2018)
Chen, W., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: BMVC, pp. 1–12 (2018)
Zhang, Y., Zhang, J., Guo, X.: Kindling the darkness: a practical low-light image enhancer. In: ACM MM, pp. 1632–1640 (2019)
Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: CVPR, pp. 97–104 (2011)
Mao, X., Li, Q., Xie, H., et al.: Least squares generative adversarial networks. In: ICCV, pp. 2794–2802 (2017)
McCann, J.: Retinex theory. Encyclopedia of Color Science and Technology, pp. 1118–1125 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Kingma, D.P., Adam, J.B.: A method for stochastic optimization. In: ICLR, pp. 1–13 (2014)
Abadi, M., Barham, P., Chen, J., Chen, Z., et al.: Tensorflow: a system for large-scale machine learning. In: Symposium on Operating Systems Design and Implementation, pp. 265–283 (2016)
Galdran, A., Alvarez-Gila, A., Bria, A., Vazquez-Corral, J., BertalmÃo, M.: On the duality between retinex and image dehazing. In: CVPR, pp. 8212–8221 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, L. et al. (2020). Learning Multi-scale Retinex with Residual Network for Low-Light Image Enhancement. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)