Abstract
Images captured in a dark environment may cause low visibility and lose significant details leading to poor performance of vision-based recognition systems. Recently, deep learning-based methods have been proposed for low-light image enhancement (LIE) with different priors or training schemes. However, even those LIE methods may introduce visual artifacts into the enhanced images. This paper proposes an adaptive LIE optimization framework that allows to re-optimize different deep learning-based LIE methods based on an adaptive quality evaluation (QE). Specifically, we design an interpretable and learnable LIE-QE module for LIE. To find the optimal structure of the LIE-QE module, we propose an algorithm unrolling method to design the LIE-QE module, where the each layer of the decomposition component of the LIE-QE module can be interpreted as WLS edge-aware smoothing. Both qualitative and quantitative experiments were conducted, and the evaluation verified the effectiveness of the proposed learnable deep unrolled LIE-QE module for LIE. The results shows that the proposed LIE framework can effectively improve different deep learning-based LIE methods indicating the potential of the optimization framework with LIE-QE module to re-optimize existing DNN-based LIE methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J., et al.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends® Mach. Learn. 3(1), 1–122 (2011)
Fan, M., Wang, W., Yang, W., Liu, J.: Integrating semantic segmentation and retinex model for low-light image enhancement. In: Proceedings of the ACM MM, pp. 2317–2325 (2020)
Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graph. 27(3), 1–10 (2008)
Fu, X., Zeng, D., Huang, Y., Zhang, X.P., Ding, X.: A weighted variational model for simultaneous reflectance and illumination estimation. In: Proceedings of CVPR, pp. 2782–2790 (2016)
Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: Proceedings of the ICML, pp. 399–406 (2010)
Guo, C., et al.: Zero-reference deep curve estimation for low-light image enhancement. In: Proceedings of CVPR, pp. 1780–1789 (2020)
Guo, X., Li, Y., Ling, H.: Lime: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982–993 (2016)
Jiang, Y., et al.: EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans. Image Process. 30, 2340–2349 (2021)
Kwon, D., Kim, G., Kwon, J.: Dale: dark region-aware low-light image enhancement. arXiv preprint arXiv:2008.12493 (2020)
Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108–129 (1977)
Land, E.H., McCann, J.J.: Lightness and retinex theory. JOSA 61(1), 1–11 (1971)
Li, C., Guo, C., Chen, C.: Learning to enhance low-light image via zero-reference deep curve estimation. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4225–4238 (2021)
Li, C., Guo, J., Porikli, F., Pang, Y.: Lightennet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recogn. Lett. 104, 15–22 (2018)
Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing low-light image enhancement via robust retinex model. IEEE Trans. Image Process. 27(6), 2828–2841 (2018)
Liu, R., Ma, L., Zhang, J., Fan, X., Luo, Z.: Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: Proceedings of CVPR, pp. 10561–10570 (2021)
Lv, F., Li, Y., Lu, F.: Attention guided low-light image enhancement with a large scale low-light simulation dataset. IJCV 129(7), 2175–2193 (2021)
Monga, V., Li, Y., Eldar, Y.C.: Algorithm unrolling: interpretable, efficient deep learning for signal and image processing. IEEE Signal Process. Mag. 38(2), 18–44 (2021)
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comput. Vis. Graphics Image Process. 39(3), 355–368 (1987)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Wang, Y., Wan, R., Yang, W., Li, H., Chau, L.P., Kot, A.: Low-light image enhancement with normalizing flow. In: Proceedings of AAAI on Artificial Intelligence, vol. 36, pp. 2604–2612 (2022)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: Proceedings of the BMVC, pp. 127–136 (2018)
Wu, W., Weng, J., Zhang, P., Wang, X., Yang, W., Jiang, J.: Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. In: Proceedings of CVPR, pp. 5901–5910 (2022)
Xu, X., Wang, R., Fu, C.W., Jia, J.: Snr-aware low-light image enhancement. In: Proceedings of CVPR, pp. 17714–17724 (2022)
Zhang, Y., Guo, X., Ma, J., Liu, W., Zhang, J.: Beyond brightening low-light images. IJCV 129, 1013–1037 (2021)
Zhang, Y., Zhang, J., Guo, X.: Kindling the darkness: a practical low-light image enhancer. In: Proceedings of the ACM MM, pp. 1632–1640 (2019)
Acknowledgements
This research was supported by the Fundamental Research Funds for the Central Universities, the Open Fund of Ministry of Education Key Laboratory of Computer Network and Information Integration (Southeast University) (K93-9-2021-01), and the Science and Technology Program of Pazhou Lab.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
He, Q., Liang, L., Xiao, W., Liang, M. (2024). Adaptive Low-Light Image Enhancement Optimization Framework with Algorithm Unrolling. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14435. Springer, Singapore. https://doi.org/10.1007/978-981-99-8552-4_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-8552-4_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8551-7
Online ISBN: 978-981-99-8552-4
eBook Packages: Computer ScienceComputer Science (R0)