Skip to main content

Advertisement

Springer Nature Link
Log in

Toward visual quality enhancement of dehazing effect with improved Cycle-GAN

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Image dehazing is a fundamental problem in computer vision. However, GT images for supervised dehazing network training are virtually impossible to obtain in the real world. Therefore, unsupervised image dehazing is of great significance. In this paper, a Cycle Generative Adversarial Network (Cycle-GAN) based on the Homology Isomerism Discriminator (HID)-assisted Detail Generation Module (DGM) is proposed to achieve image dehazing under unsupervised training. In order to enable the generator to recover the details of the entire image, especially in images with complex structures, DGM is developed to boost the details performance of the output dehazing results. Then, HID is proposed to boost dehazing performance based on heterogeneous features and Channel-Spatial Attention (CSA) and complement DGM by varied guidance to the generator. Next, the loss functions are updated according to the image dehazing task based on Cycle-GAN under unsupervised learning. Finally, the experimental results under ablation study and comparison to state-of-the-art demonstrate that the proposed method has attractive results in both visual experience and quantitative metrics under various datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig.5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The O-haze, Dense-Haze, NH-HAZE datasets analyzed during the current study are respectively available at https://data.vision.ee.ethz.ch/cvl/ntire18//o-haze/, https://data.vision.ee.ethz.ch/cvl/ntire19//dense-haze/, https://data.vision.ee.ethz.ch/cvl/ntire20/nh-haze/.

References

  1. Abdulkareem K, Arbaiy N, Zaidan AA et al (2020) A new standardisation and selection framework for real-time image dehazing algorithms from multi-foggy scenes based on fuzzy Delphi and hybrid multi-criteria decision analysis methods. Neural Comput Appl 33(4):1029–1054

    Article  Google Scholar 

  2. Shi ZH, Feng YN, Zhao MH et al (2020) A joint deep neural networks-based method for single nighttime rainy image enhancement. Neural Comput Appl 32(7):1913–1926

    Article  Google Scholar 

  3. Zhang XQ, Wang T, Luo WH (2021) Multi-level fusion and attention-guided CNN for image Dehazing. IEEE Trans Circuits Syst Video Technol 31(11):4162–4173

    Article  Google Scholar 

  4. Choi LK, You J, Bovik AC (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–4390

    Article  MathSciNet  MATH  Google Scholar 

  5. Galdran A, Vazquez-Corral J, Pardo D et al (2017) Fusion-based variational image dehazing. IEEE Signal Process Lett 24(2):151–155

    MATH  Google Scholar 

  6. Lian XH, Pang YW, Yang AP (2018) Learning intensity and detail mapping parameters for dehazing. Multimed Tools Appl 77(12):15695–15720

    Article  Google Scholar 

  7. Mathur M, Goel N (2021) Enhancement algorithm for high visibility of underwater images. IET Image Proc. https://doi.org/10.1049/ipr2.12210

    Article  Google Scholar 

  8. He KM, Sun J, Tang XO (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353

    Article  Google Scholar 

  9. Berman D, Treibitz T and Avidan S (2016) Non-local image dehazing. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1674–1682

  10. Wang WC, Yuan XH, Wu XJ et al (2017) Fast image dehazing method based on linear transformation. IEEE Trans Multimed 19(6):1142–1155

    Article  Google Scholar 

  11. Yang Y, Liu C (2021) Single image dehazing using elliptic curve scattering model. SIViP. https://doi.org/10.1007/s11760-021-01876-8

    Article  Google Scholar 

  12. Li BY, Peng XL, Wang ZY et al. (2017) AOD-Net: all-in-one dehazing network. In: IEEE international conference on computer vision, pp 4770–4778

  13. Cai BL, Xu XM, Jia K et al (2016) DehazeNet: an end-to-end system for single image haze removal. IEEE Trans Image Process 25(11):5187–5198

    Article  MathSciNet  MATH  Google Scholar 

  14. Fahim M, Jung HY (2021) Single image dehazing using end-to-end deep-dehaze network. Electronics 10(7)

  15. Zhang SD, He FZ, Ren WQ (2020) NLDN: non-local dehazing network for dense haze removal. Neurocomputing 410:363–373

    Article  Google Scholar 

  16. Zhang SD, He FZ (2019) DRCDN: learning deep residual convolutional dehazing networks. Visual Computer 36(9):1797–1808

    Article  Google Scholar 

  17. Pang YW, Xie J, Li XL (2019) Visual haze removal by a unified generative adversarial network. IEEE Trans Circuits Syst Video Technol 29(11):3211–3221

    Article  Google Scholar 

  18. Deniz E, Anil G and Hazim K (2018) Cycle-Dehaze: enhanced CycleGAN for single image dehazing. In: 2018 IEEE/CVF conference on computer vision and pattern recognition workshops, pp 938–946

  19. Park J, Han DK, Ko H (2020) Fusion of heterogeneous adversarial networks for single image dehazing. IEEE Trans Image Process 29:4721–4732

    Article  MATH  Google Scholar 

  20. Sun ZY, Zhang YF, Bao FX et al (2021) ICycleGAN: single image dehazing based on iterative dehazing model and CycleGAN. Comput Vis Image Underst 203:103133

    Article  Google Scholar 

  21. Chen JH, Wu C, Chen H (2020) Unsupervised dark-channel attention-guided CycleGAN for single-image dehazing. Sensors 20(21):6000

    Article  Google Scholar 

  22. Golts A, Freedman D, Elad M (2020) Unsupervised single image dehazing using dark channel prior loss. IEEE Trans Image Process 29:2692–2701

    Article  MATH  Google Scholar 

  23. Goodfellow IJ, Pouget-Abadie J, Mirza M (2014) Generative adversarial nets. Adv Neural Inform Process Syst 27:2672–2680

    Google Scholar 

  24. Zhu JY, Park T, Isola P (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE international conference on computer vision, pp 2242–2251

  25. Kingma D, Ba J (2014) Adam: a method for stochastic optimization. In: International conference on learning representations. ISSN 09252312. https://doi.org/10.1145/1830483.1830503. URL: http://arxiv.org/abs/1412.6980

  26. Mittal A, Soundararajan R, Bovik AC (2013) Making a completely blind image quality analyzer. IEEE Signal Process Lett 20(3):209–212

    Article  Google Scholar 

  27. Girod B (1993) What’s wrong with mean-squared error. In: Watson AB (ed) Digital images and human vision. MIT Press, Cambridge, MA, pp 207–220

    Google Scholar 

  28. Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Article  Google Scholar 

  29. Thanh LT, Thanh DNH, Hue NM et al (2019) Single image dehazing based on adaptive histogram equalization and linearization of gamma correction. In: Proceedings of 2019 25th Asia-Pacific conference on communications (APCC), pp 36–40

  30. Liu XH, Ma YR, Shi ZH et al (2019) GridDehazeNet: attention-based multi-scale network for image dehazing. In: IEEE international conference on computer vision, pp 7313–7322

  31. Dong H, Pan JS, Xiang L et al (2020) Multi-scale boosted dehazing network with dense feature fusion. In: IEEE conference on computer vision and pattern recognition

  32. Galdran A (2018) Image dehazing by artificial multiple-exposure image fusion. Signal Process 149:135–147

    Article  Google Scholar 

  33. Li BY, Guo YB, Gu SH et al (2021) You only look yourself: unsupervised and untrained single image dehazing neural network. Int J Comp Vision 129(5):1754–1767

    Article  Google Scholar 

  34. Chen ZY, Wang YC, Yang Y et al. (2021) PSD: principled synthetic-to-real dehazing guided by physical priors. In: 2021 IEEE/CVF conference on computer vision and pattern recognition, pp 7176–7185

  35. Zhou XZ, Su WJ, Lu LW et al. (2020) Deformable DETR:deformable transformers for end-to-end object detection. In: International conference on learning representations, URL: https://arxiv.org/abs/2010.04159

Download references

Funding

Key R&D program of Jiangsu Province, BE2021679, Tao Zhang.

Author information

Authors and Affiliations

  1. Southeast University, Nanjing, China

    Xiaochen Liu & Tao Zhang

  2. North University of China, 030051, Taiyuan, China

    Jiawei Zhang

Authors
  1. Xiaochen Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Tao Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Jiawei Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Tao Zhang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, X., Zhang, T. & Zhang, J. Toward visual quality enhancement of dehazing effect with improved Cycle-GAN. Neural Comput & Applic 35, 5277–5290 (2023). https://doi.org/10.1007/s00521-022-07964-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07964-1

Keywords