Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement

Xingyu  Pan; Fengling  Chen

doi:10.6180/jase.202601_29(1).0012

Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement

Xingyu Pan¹This email address is being protected from spambots. You need JavaScript enabled to view it. and Fengling Chen²

¹School of Electronic and Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou, 450064, China

²Zhengzhou Electric Power College, Zhengzhou, 450003, China

Received: October 9, 2024
Accepted: April 19, 2025
Publication Date: May 1, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202601_29(1).0012

Low-quality image enhancement methods can effectively improve image quality and details, which have attracted great attention in various fields. However, current methods still face with two issues: (1) They commonly earn a deterministic generation mapping between low-quality and normal images via relying on pixel-level reconstruction, leading to improper brightness and noise in the enhancing process. (2) They use only one type of generative model, either explicit or implicit, which limits flexibility and efficiency of models. To this end, a novel flow-based generative adversarial network with dual attention (FGAN-DA) is devised for data generation. Specifically, FGAN-DA constructs a hybrid generative model via combining explicit and implicit components within the GAN architecture, which effectively alleviates detail blurred and singularity caused by sole generation modeling. FGAN-DA comprises the dual attention feature extraction, invertible flow generation network, the Markov discriminant network. The three modules seamlessly collaborate in enhancing images with good perceptual quality, which effectively boosts the performance of FGAN-DA. Finally, quantitative metrics and visual quality evaluations demonstrate that FGAN-DA sets a new baseline in can generate images with good perceptual quality.

Keywords: Data generation; dual attention; flow generative network

[1] Y. Liu, T. Huang, W. Dong, F. Wu, X. Li, and G. Shi. “Low-light image enhancement with multi-stage residue quantization and brightness-aware atten tion”. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023, 12140–12149.
[2] Y.Gao, W.Zhang, H.He, L.Cao, Y. Zhang, Z. Huang, and X. Zhao, (2024) “TSSFN: Transformer-based self supervised fusion network for low-quality fundus image enhancement" Biomedical Signal Processing and Control 89: 105768. DOI: 10.1016/j.bspc.2023.105768.
[3] P. Li, Z. Chen, L. T. Yang, Q. Zhang, and M. J. Deen, (2017) “Deep convolutional computation model for feature learning on big data in internet of things" IEEE Transactions on Industrial Informatics 14(2): 790–798. DOI: 10.1109/TII.2017.2739340.
[4] P. Li, A. A. Laghari, M. Rashid, J. Gao, T. R. Gadekallu, A. R. Javed, and S. Yin, (2022) “A deep multimodal adversarial cycle-consistent network for smart enterprise system" IEEE Transactions on Industrial Informatics 19(1): 693–702. DOI: 10.1109/TII.2022.3197201.
[5] P. Li, J. Gao, J. Zhang, S. Jin, and Z. Chen, (2022) “Deep Reinforcement Clustering" IEEE Transactions on Multimedia: DOI: 10.1109/TMM.2022.3233249.
[6] K.G.Lore, A.Akintayo, and S. Sarkar, (2017) “LLNet: Adeep autoencoder approach to natural low-light image enhancement" Pattern Recognition 61: 650–662. DOI: 10.1016/j.patcog.2016.06.008.
[7] X. Cheng, J. Zhou, J. Song, and X. Zhao, (2023) “A highway traffic image enhancement algorithm based on improved GAN in complex weather conditions" IEEE Transactions on Intelligent Transportation Systems 24(8): 8716–8726. DOI: 10.1109/TITS.2023.3258063.
[8] R. Cong, W. Yang, W. Zhang, C. Li, C.-L. Guo, Q. Huang, and S. Kwong, (2023) “Pugan: Physical model guided underwater image enhancement using gan with dual-discriminators" IEEE Transactions on Image Processing 32: 4472–4485. DOI: 10.1109/TIP.2023.3286263.
[9] L. Shen, Z. Yue, F. Feng, Q. Chen, S. Liu, and J. Ma, (2017) “Msr-net: Low-light image enhancement using deep convolutional network" arXiv preprint arXiv:1711.02488: DOI: 10.48550/arXiv.1711.02488.
[10] C. Wei, W. Wang, W. Yang, and J. Liu, (2018) “Deep retinex decomposition for low-light enhancement" arXiv preprint arXiv:1808.04560: DOI: 10.48550/arXiv.1808.04560.
[11] Y. Zhang, J. Zhang, and X. Guo. “Kindling the dark ness: A practical low-light image enhancer”. In: Proceedings of the 27th ACM international conference on multimedia. 2019, 1632–1640. DOI: DOI:10.1145/3343031.335092.
[12] Y.Jiang, X.Gong, D.Liu, Y.Cheng, C.Fang, X.Shen, J. Yang, P. Zhou, and Z. W. Enlightengan, (2021) “Deep light enhancement without paired supervision., 2021, 30" DOI: https://doi. org/10.1109/TIP: 2340–2349. DOI: 10.1109/TIP.2021.3051462.
[13] Y. Zhang, X. Di, B. Zhang, and C. Wang, (2020) “Self-supervised image enhancement network: Training with low light images only" arXiv preprint arXiv:2002.11300: DOI: 10.48550/arXiv.2002.11300.
[14] C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, and R. Cong. “Zero-reference deep curve estima tion for low-light image enhancement”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020, 1780–1789. DOI: 10.1109/CVPR42600.2020.00185.
[15] T.Ma, M.Guo, Z.Yu, Y.Chen, X.Ren, R.Xi, Y.Li,and X. Zhou, (2021) “Retinex GAN: Unsupervised low-light enhancement with two-layer convolutional decomposition networks" IEEE Access 9: 56539–56550. DOI: 10.1109/ ACCESS.2021.3072331.
[16] C.-M. Fan, T.-J. Liu, and K.-H. Liu. “Half wavelet at tention on m-net+ for low-light image enhancement”. In: 2022 IEEE International Conference on Image Processing (ICIP). 2022, 3878–3882. DOI: 10.48550/arXiv.2203.01296.
[17] Y. Wang, R. Wan, W. Yang, H. Li, L.-P. Chau, and A. Kot. “Low-light image enhancement with normalizing flow”. In: Proceedings of the AAAI conference on artificial intelligence. 36. 3. 2022, 2604–2612. DOI: 10.1609/aaai.v36i3.20162.
[18] X. Guo and Q. Hu, (2023) “Low-light image enhancement via breaking down the darkness" International Journal of Computer Vision 131(1): 48–66. DOI: 10.1007/s11263-022-01667-9.
[19] J. Liang, Y. Xu, Y. Quan, B. Shi, and H. Ji, (2022) “Self supervised low-light image enhancement using discrepant untrained network priors" IEEE Transactions on Circuits and Systems for Video Technology 32(11): 7332–7345. DOI: 10.1109/tcsvt.2022.3181781.
[20] Z. Zhao, B. Xiong, L. Wang, Q. Ou, L. Yu, and F. Kuang, (2021) “RetinexDIP: A unified deep framework for low-light image enhancement" IEEE Transactions on Circuits and Systems for Video Technology 32(3): 1076–1088. DOI: 10.1109/tcsvt.2021.3073371.

Latest Articles