Abstract
The low visibility of low-light images due to lack of exposure poses a significant challenge for vision tasks such as image fusion, detection and segmentation in low-light conditions. Real-world situations such as backlighting and shadow occlusion mostly exist with non-uniform low-light, while existing enhancement methods tend to brighten both low-light and normal-light regions, we actually prefer to enhance dark regions but suppress overexposed regions. To address this problem, we propose a new non-uniform dark visual network (NDVN) that uses the attention mechanism to enhance regions with different levels of illumination separately. Since deep-learning needs strong data-driven, for this purpose we carefully construct a non-uniform dark synthetic dataset (UDL) that is larger and more diverse than existing datasets, and more importantly it contains more non-uniform light states. We use the manually annotated luminance domain mask (LD-mask) in the dataset to drive the network to distinguish between low-light and extremely dark regions in the image. Guided by the LD-mask and the attention mechanism, the NDVN adaptively illuminates different light regions while enhancing the color and contrast of the image. More importantly, we introduce a new region loss function to constrain the network, resulting in better quality enhancement results. Extensive experiments show that our proposed network outperforms other state-of-the-art methods both qualitatively and quantitatively.
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
Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: British Machine Vision Conference, 155p (2018)
Cai, J., Gu, S., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Process. 27(4), 2049–2062 (2018)
Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input/output image pairs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 97–104(2011)
Chen, C., Chen, Q., Xu, J., Koltun, V.: Learning to see in the dark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3291–3300 (2018)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans.Comput. Imaging 3(1), 47–57 (2017)
Hahner, M., Dai, D., Sakaridis, C., Zaech, N.J., Gool, V.L.: Semantic understanding of foggy scenes with purely synthetic data. In: IEEE Intelligent Transportation Systems Conference, pp. 3675–3681 (2019)
Xu, K., Yang, X., Yin, B., Lau, H.W.R.: Learning to restore low-light images via decomposition-and-enhancement. In: Conference on Computer Vision and Pattern Recognition, pp. 2278–2287(2020)
Yang, W., Wang, S., Wang, Y: Band representation-based semi-supervised low-light image enhancement: bridging the gap between signal fidelity and perceptual quality. IEEE Trans. Image Process. 30, 3461–3473 (2021)
Ibrahim, H., Kong, N.: Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Trans. Consum. Electron. 53(4), 1752–1758 (2007)
Abdullah-Al-Wadud, M., Kabir, H.M., Akber Dewan, A.M., Chae, O.: A dynamic histogram equalization for image contrast enhancement. IEEE Trans. Consum. Electr. 53(2), 593–600(2007)
Jobson, D.J., Rahman, Z., Woodell, A.G.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (2002)
Gu, Z., Li, F., Fang, F., Zhang, G.: A Novel retinex-based fractional-order variational model for images with severely low light. IEEE Trans. Image Process. 24, 3239–3253 (2020)
Hu, X., Jiang, Y., Fu, W.C., Heng, A.P.: Mask-ShadowGAN: learning to remove shadows from unpaired data. In: International Conference on Computer Vision, pp. 2278–2287(2019)
Zhou, S., Li C., and Loy C.C.: LEDNet: Joint Low-light Enhancement and Deblurring in the Dark. European Conference on Computer Vision, (2022). https://doi.org/10.1007/978-3-031-20068-7_33
Ibrahim, H., Kong, N.: Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Trans. Consum. Electron. 53(4), 1752–1758 (2007)
Nakai, K., Hoshi, Y., Taguchi, A.: Color image contrast enhacement method based on differential intensity/saturation gray-levels histograms. In: International Symposium on Intelligent Signal Processing and Communications Systems, pp. 445–449 (2013)
Sheikh, H.R., Bovik, A.C.: Image information and visual quality. IEEE Trans. Image Process. 15(2), 430–444 (2006)
Chen, Z., Abidi, B.R., Page, D.L., Abidi, M.A.: Graylevel grouping (GLG): an automatic method for optimized image contrast enhancement-Part I: the basic method. IEEE Trans. Image Process. 15(8), 2290–2302 (2006)
Jiang, Y.: EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans. Image Process. 30, 2340–2349 (2021)
Lv, F., Li, Y., Lu, F.: Attention guided low-light image enhancement with a large scale low-light simulation dataset. Int. J. Comput. Vision 129(4), 2175–2193 (2019)
Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982–993 (2017)
Wang, Z.: Image quality assessment : from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
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)
Lore, K.G., Akintayo, A., Sarkar, S.: LLNet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recogn. 61, 650–662 (2017)
Lv, F., Li, Y., Wu, J., Lim, C.: MBLLEN: low-light image/video enhancement using CNNs. In: British Machine Vision Conference, 220p (2018)
Li, X., Wang, W., Hu, X.: Selective Kernel networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510–519 (2019)
Fan, C.M., Liu T.J., Liu K.H.: Half wavelet attention on M-Net+ for L image enhancement. In: International Conference on Image Processing (2022)
Kwon, D., Kim G., and Liu J. Kwon.: DALE: dark region-aware low-light image enhancement. In: British Machine Vision Conference, 1025p. (2020)
Zhang, Y., Zhang, J., Guo, X.: Kindling the darkness: a practical low-light image enhancer. In: International Conference on Multimedia 1(9), 1632–1640 (2019)
Zhang, Y., Guo, X., Ma, J., Liu, W., Zhang, J.: Beyond brightening low-light images. Int. J. Comput. Vision 129(4), 1013–1037 (2021). https://doi.org/10.1007/s11263-020-01407-x
Liu, J., Xu, D., Yang, W., Fan, M., Huang, H.: Benchmarking low-light image enhancement and beyond. Int. J. Comput. Vision 129(4), 1153–1184 (2021). https://doi.org/10.1007/s11263-020-01418-8
Guo C., Li C., Guo J., Loy C. C., Hou J., and Cong R.: Zero-reference deep curve estimation for low-light image enhancement. In: Conference on Computer Vision and Pattern Recognition, pp. 1780–1789 (2020)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Cai, F., Tu, Y., Ding, Y. (2023). Low-Light Image Enhancement Under Non-uniform Dark. In: Dang-Nguyen, DT., et al. MultiMedia Modeling. MMM 2023. Lecture Notes in Computer Science, vol 13834. Springer, Cham. https://doi.org/10.1007/978-3-031-27818-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-27818-1_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27817-4
Online ISBN: 978-3-031-27818-1
eBook Packages: Computer ScienceComputer Science (R0)