{"id":1647,"date":"2026-03-29T19:17:19","date_gmt":"2026-03-29T11:17:19","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=1647"},"modified":"2026-05-23T19:39:40","modified_gmt":"2026-05-23T11:39:40","slug":"adaptive-context-aware-generative-adversarial-network-for-low-quality-image-enhancement","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=adaptive-context-aware-generative-adversarial-network-for-low-quality-image-enhancement","title":{"rendered":"Adaptive Context-Aware Generative Adversarial Network for Low-quality Image Enhancement"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 29, Issue 1<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Xingyu Pan1<\/sup><\/i><\/a> and Fengling Chen2<\/sup><\/p>\n\n\n\n

1<\/sup>School of Electronic and Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou, 450064, China<\/p>\n\n\n\n

2<\/sup>Zhengzhou Electric Power College, Zhengzhou, 450003, China<\/p>\n<\/div>\n\n\n\n

\n

Received:\u00a0October 9, 2024
Accepted:\u00a0April 19, 2025
Publication Date:\u00a0March 29, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

The illustration of FGAN-DA<\/p>\n<\/div>\n<\/div>\n\n\n\n

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

Download Citation:\u00a0 BibTeX <\/a>| https:\/\/doi.org\/10.6180\/jase.202601_29(1).0012<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

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.<\/p>\n\n\n\n

Keywords:\u00a0Data generation; dual attention; flow generative network<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] Y. Liu, T. Huang, W. Dong, F. Wu, X. Li, and G. Shi. \u201cLow-light image enhancement with multi-stage residue quantization and brightness-aware attention\u201d. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023, 12140\u201312149.<\/li>\n
  2. [2] Y. Gao, W. Zhang, H. He, L. Cao, Y. Zhang, Z. Huang, and X. Zhao, (2024) \u201cTSSFN: Transformer-based self-supervised fusion network for low-quality fundus image enhancement\u201d Biomedical Signal Processing and Control 89: 105768. DOI: 10.1016\/j.bspc.2023.105768.<\/li>\n
  3. [3] P. Li, Z. Chen, L. T. Yang, Q. Zhang, and M. J. Deen, (2017) \u201cDeep convolutional computation model for feature learning on big data in internet of things\u201d IEEE Transactions on Industrial Informatics 14(2): 790\u2013798. DOI: 10.1109\/TII.2017.2739340.<\/li>\n
  4. [4] P. Li, A. A. Laghari, M. Rashid, J. Gao, T. R. Gadekallu, A. R. Javed, and S. Yin, (2022) \u201cA deep multimodal adversarial cycle-consistent network for smart enterprise system\u201d IEEE Transactions on Industrial Informatics 19(1): 693\u2013702. DOI: 10.1109\/TII.2022.3197201.<\/li>\n
  5. [5] P. Li, J. Gao, J. Zhang, S. Jin, and Z. Chen, (2022) \u201cDeep Reinforcement Clustering\u201d IEEE Transactions on Multimedia: DOI: 10.1109\/TMM.2022.3233249.<\/li>\n
  6. [6] K. G. Lore, A. Akintayo, and S. Sarkar, (2017) \u201cLLNet: A deep autoencoder approach to natural low-light image enhancement\u201d Pattern Recognition 61: 650\u2013662. DOI: 10.1016\/j.patcog.2016.06.008.<\/li>\n
  7. [7] X. Cheng, J. Zhou, J. Song, and X. Zhao, (2023) \u201cA highway traffic image enhancement algorithm based on improved GAN in complex weather conditions\u201d IEEE Transactions on Intelligent Transportation Systems 24(8): 8716\u20138726. DOI: 10.1109\/TITS.2023.3258063.<\/li>\n
  8. [8] R. Cong, W. Yang, W. Zhang, C. Li, C.-L. Guo, Q. Huang, and S. Kwong, (2023) \u201cPugan: Physical model-guided underwater image enhancement using gan with dual-discriminators\u201d IEEE Transactions on Image Processing 32: 4472\u20134485. DOI: 10.1109\/TIP.2023.3286263.<\/li>\n
  9. [9] L. Shen, Z. Yue, F. Feng, Q. Chen, S. Liu, and J. Ma, (2017) \u201cMsr-net: Low-light image enhancement using deep convolutional network\u201d arXiv preprint arXiv:1711.02488: DOI: 10.48550\/arXiv.1711.02488.<\/li>\n
  10. [10] C. Wei, W. Wang, W. Yang, and J. Liu, (2018) \u201cDeep retinex decomposition for low-light enhancement\u201d arXiv preprint arXiv:1808.04560: DOI: 10.48550\/arXiv.1808.04560.<\/li>\n
  11. [11] Y. Zhang, J. Zhang, and X. Guo. \u201cKindling the darkness: A practical low-light image enhancer\u201d. In: Proceedings of the 27th ACM international conference on multimedia. 2019, 1632\u20131640. DOI: 10.1145\/3343031.335092.<\/li>\n
  12. [12] Y. Jiang, X. Gong, D. Liu, Y. Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, and Z. W. EnlightenGan, (2021) \u201cDeep light enhancement without paired supervision., 2021, 30\u201d DOI: https:\/\/doi.org\/10.1109\/TIP<\/a>: 2340\u20132349. DOI: 10.1109\/TIP.2021.3051462.<\/li>\n
  13. [13] Y. Zhang, X. Di, B. Zhang, and C. Wang, (2020) \u201cSelf-supervised image enhancement network: Training with low light images only\u201d arXiv preprint arXiv:2002.11300: DOI: 10.48550\/arXiv.2002.11300.<\/li>\n
  14. [14] C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, and R. Cong. \u201cZero-reference deep curve estimation for low-light image enhancement\u201d. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020, 1780\u20131789. DOI: 10.1109\/CVPR42600.2020.00185.<\/li>\n
  15. [15] T. Ma, M. Guo, Z. Yu, Y. Chen, X. Ren, R. Xi, Y. Li, and X. Zhou, (2021) \u201cRetinexGAN: Unsupervised low-light enhancement with two-layer convolutional decomposition networks\u201d IEEE Access 9: 56539\u201356550. DOI: 10.1109\/ACCESS.2021.3072331.<\/li>\n
  16. [16] C.-M. Fan, T.-J. Liu, and K.-H. Liu. \u201cHalf wavelet attention on m-net+ for low-light image enhancement\u201d. In: 2022 IEEE International Conference on Image Processing (ICIP). 2022, 3878\u20133882. DOI: 10.48550\/arXiv.2203.01296.<\/li>\n
  17. [17] Y. Wang, R. Wan, W. Yang, H. Li, L.-P. Chau, and A. Kot. \u201cLow-light image enhancement with normalizing flow\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 36. 3. 2022, 2604\u20132612. DOI: 10.1609\/aaai.v36i3.20162.<\/li>\n
  18. [18] X. Guo and Q. Hu, (2023) \u201cLow-light image enhancement via breaking down the darkness\u201d International Journal of Computer Vision 131(1): 48\u201366. DOI: 10.1007\/s11263-022-01667-9.<\/li>\n
  19. [19] J. Liang, Y. Xu, Y. Quan, B. Shi, and H. Ji, (2022) \u201cSelf-supervised low-light image enhancement using discrepant untrained network priors\u201d IEEE Transactions on Circuits and Systems for Video Technology 32(11): 7332\u20137345. DOI: 10.1109\/tcsvt.2022.3181781.<\/li>\n
  20. [20] Z. Zhao, B. Xiong, L. Wang, Q. Ou, L. Yu, and F. Kuang, (2021) \u201cRetinexDIP: A unified deep framework for low-light image enhancement\u201d IEEE Transactions on Circuits and Systems for Video Technology 32(3): 1076\u20131088. DOI: 10.1109\/tcsvt.2021.3073371.<\/li>\n<\/ol>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,15,6,116],"tags":[133],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" 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:\u00a0 BibTeX | https:\/\/doi.org\/10.6180\/jase.202601_29(1).0012\u00a0\u00a0 Download PDF Low-quality image enhancement methods can effectively improve image quality and details,…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/1647"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1647"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1647"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1647"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}