Abstract
The deep learning-based low-light image enhancement task aims to learn a mapping that converts low-light images to normally exposed images by training with paired or unpaired datasets. Most of these existing methods are based on convolutional neural networks, which largely limits the network’s ability to learn global information. Meanwhile, the reconstruction loss or adversarial loss they adopt often cannot accurately measure the visual distance between the prediction and the target, resulting in blurred regions in the enhancement results. In this paper, we propose a novel flow learning based dual networks (FDN), which consists of a dual network and a flow learning based model. The dual network is mainly composed of a reidual-based Unet encoder and a residual-based Swin Transformer encoder, which can make up for the lack of global information processing and has more advantages in processing deep and shallow information. Moreover, we use a single loss function named negative log-likelihood to train the entire network, which enables the flow models to adequately learn the complex conditional distribution of normally exposed images and avoid blurry outputs. Experimental results on two benchmark datasets show that the proposed FDN method can achieve the sate-of-the-art performances on low-light image enhancement task.
Similar content being viewed by others
References
Li C, Guo C, Han L-H, Jiang J, Cheng M-M, Gu J, Loy CC (2021) Low-light image and video enhancement using deep learning: a survey. IEEE Trans Pattern Anal Mach Intell 44:9396–9416
Liu J, Xu D, Yang W, Fan M, Huang H (2021) Benchmarking low-light image enhancement and beyond. Int J Comput Vis 129(4):1153–1184
Wang H, Peng J, Chen D, Jiang G, Zhao T, Fu X (2020) Attribute-guided feature learning network for vehicle reidentification. IEEE Multimedia 27(4):112–121
Ibrahim H, Kong NSP (2007) Brightness preserving dynamic histogram equalization for image contrast enhancement. IEEE Trans Consum Electron 53(4):1752–1758
Abdullah-Al-Wadud M, Kabir MH, Dewan MAA, Chae O (2007) A dynamic histogram equalization for image contrast enhancement. In: 2007 digest of technical papers international conference on consumer electronics, pp 1–2. https://doi.org/10.1109/ICCE.2007.341567
Wang S, Zheng J, Hu H-M, Li B (2013) Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans Image Process 22(9):3538–3548
Guo X, Li Y, Ling H (2016) Lime: low-light image enhancement via illumination map estimation. IEEE Trans Image Process 26(2):982–993
Lore KG, Akintayo A, Sarkar S (2017) LLNet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recognit 61:650–662
Wei C, Wang W, Yang W, Liu J (2018) Deep Retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560
Zhang Y, Zhang J, Guo X (2019) Kindling the darkness: a practical low-light image enhancer. In: Proceedings of the 27th ACM international conference on multimedia, pp 1632–1640
Triantafyllidou D, Moran S, McDonagh S, Parisot S, Slabaugh G (2020) Low light video enhancement using synthetic data produced with an intermediate domain mapping. In: European conference on computer vision. Springer, pp 103–119
Yang W, Wang S, Fang Y, Wang Y, Liu J (2020) From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3063–3072
Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Yang J, Zhou P, Wang Z (2021) EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans Image Process 30:2340–2349
Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R (2020) Zero-reference deep curve estimation for low-light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1780–1789
Jaini P, Kobyzev I, Yu Y, Brubaker M (2020) Tails of Lipschitz triangular flows. In: International conference on machine learning. PMLR, pp 4673–4681
Dinh L, Krueger D, Bengio Y (2014) Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516
Dinh L, Sohl-Dickstein J, Bengio S (2016) Density estimation using real NVP. arXiv preprint arXiv:1605.08803
Kingma DP, Dhariwal P (2018) Glow: generative flow with invertible 1x1 convolutions. Adv Neural Inf Process Syst 31
Lugmayr A, Danelljan M, Gool LV, Timofte R (2020) Srflow: learning the super-resolution space with normalizing flow. In: European conference on computer vision. Springer, pp 715–732
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Wang H, Yao M, Jiang G, Mi Z, Fu X (2023) Graph-collaborated auto-encoder hashing for multi-view binary clustering. arXiv preprint arXiv:2301.02484
Wang H, Jiang G, Peng J, Deng R, Fu X (2022) Towards adaptive consensus graph: multi-view clustering via graph collaboration. IEEE Trans Multimedia
Wang H, Wang Y, Zhang Z, Fu X, Zhuo L, Xu M, Wang M (2020) Kernelized multiview subspace analysis by self-weighted learning. IEEE Trans Multimedia 23:3828–3840
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 10012–10022
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30
Wang Y, Wan R, Yang W, Li H, Chau L-P, Kot A (2022) Low-light image enhancement with normalizing flow. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 2604–2612
Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M-H, Shao L (2020) Learning enriched features for real image restoration and enhancement. In: European conference on computer vision. Springer, pp 492–511
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141
Woo S, Park J, Lee J-Y, Kweon, IS (2018) CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3–19
Ying Z, Li G, Ren Y, Wang R, Wang W (2017) A new low-light image enhancement algorithm using camera response model. In: The IEEE international conference on computer vision (ICCV)
Hu C-H, Yu J, Wu F, Zhang Y, Jing X-Y, Lu X-B, Liu P (2021) Face illumination recovery for the deep learning feature under severe illumination variations. Pattern Recognit 111:107724
Risheng L, Long M, Jiaao Z, Xin F, Zhongxuan L (2021) Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zhang Y, Guo X, Ma J, Liu W, Zhang J (2021) Beyond brightening low-light images. Int J Comput Vis 129(4):1013–1037
Xu X, Wang R, Fu C-W, Jia J (2022) SNR-aware low-light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 17714–17724
Yang W, Wang W, Huang H, Wang S, Liu J (2021) Sparse gradient regularized deep Retinex network for robust low-light image enhancement. IEEE Trans Image Process 30:2072–2086
Bychkovsky V, Paris S, Chan E, Durand F (2011) Learning photographic global tonal adjustment with a database of input/output image pairs. In: CVPR 2011. IEEE, pp 97–104
Park J, Lee J-Y, Yoo D, Kweon IS (2018) Distort-and-recover: color enhancement using deep reinforcement learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5928–5936
Gharbi M, Chen J, Barron JT, Hasinoff SW, Durand F (2017) Deep bilateral learning for real-time image enhancement. ACM Trans Graph TOG 36(4):1–12
Chen Y-S, Wang Y-C, Kao M-H, Chuang Y-Y (2018) Deep photo enhancer: unpaired learning for image enhancement from photographs with GANs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6306–6314
Wang R, Zhang Q, Fu C-W, Shen X, Zheng W-S, Jia J (2019) Underexposed photo enhancement using deep illumination estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6849–6857
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Loh YP, Chan CS (2019) Getting to know low-light images with the exclusively dark dataset. Comput Vis Image Underst 178:30–42
Funding
This work was supported by the National Natural Science Foundation of China under Grant 62272240 and Grant 61802203, and in part by the Nanjing University of Posts and Telecommunications Science Foundation under Grant NY221081.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, S., Hu, C., Yi, W. et al. Flow Learning Based Dual Networks for Low-Light Image Enhancement. Neural Process Lett 55, 8115–8130 (2023). https://doi.org/10.1007/s11063-023-11303-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-023-11303-3