Skip to main content
SpringerLink
Log in

BPFD-Net: enhanced dehazing model based on Pix2pix framework for single image

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

In this paper, we propose an image dehazing model based on the generative adversarial networks (GAN). The pix2pix framework is taken as the starting point in the proposed model. First, a UNet-like network is employed as the dehazing network in view of the high consistency of the image dehazing problem. In the proposed model, a shortcut module is proposed to effectively increase the nonlinear characteristics of the network, which is beneficial for subsequent processes of image generation and stabilizing the training process of the GAN network. Also, inspired by the face illumination processing model and the perceptual loss model, the quality vision loss strategy is designed to obtain a better visual quality of the dehazed image, based on peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and perceptual losses. The experimental results on public datasets show that our network demonstrates the superiority over the compared models on indoor images. Also, the dehazed image by the proposed model shows better chromaticity and qualitative quality.

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

Access this article

Log in via an institution

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
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Agarwal, T.K., Tiwari, M., Lamba, S.S.: Modified histogram based contrast enhancement using homomorphic filtering for medical images. In: 2014 IEEE International Advance Computing Conference (IACC), pp. 964–968

  2. Akbarizadeh, G.: A new statistical-based kurtosis wavelet energy feature for texture recognition of SAR images. IEEE Trans. Geosci. Remote Sens. 50(11), 4358–4368 (2012)

    Article  Google Scholar 

  3. Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: Dehazenet: An end-to-end system for single image haze removal. IEEE Trans. Image Process. 25(11), 5187–5198 (2016)

    Article  MathSciNet  Google Scholar 

  4. Chen, D., He, M., Fan, Q., Liao, J., Zhang, L., Hou, D., Yuan, L., Hua, G.: Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1375–1383

  5. Davari, N., Akbarizadeh, G., Mashhour, E.: Intelligent diagnosis of incipient fault in power distribution lines based on corona detection in uv-visible videos. IEEE Trans. Power Deliv. (2020)

  6. Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., Yang, M.H.: Multi-scale boosted dehazing network with dense feature fusion. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2154–2164

  7. Dong, Y., Liu, Y., Zhang, H., Chen, S., Qiao, Y.: Fd-gan: Generative adversarial networks with fusion-discriminator for single image dehazing. Proc. AAAI Conf. Artif. Intell. 34, 10729–10736 (2020)

    Google Scholar 

  8. Fu, X., Wang, J., Zeng, D., Huang, Y., Ding, X.: Remote sensing image enhancement using regularized-histogram equalization and DCT. IEEE Geosci. Remote Sens. Lett. 12(11), 2301–2305 (2015)

    Article  Google Scholar 

  9. Gu, Y., Yang, X., Gao, Y.: A novel total generalized variation model for image dehazing. J. Math. Imaging Vis. 61(9), 1329–1341 (2019)

    Article  MathSciNet  Google Scholar 

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

    Article  Google Scholar 

  11. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778

  12. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708

  13. Im, J., Yoon, I., Hayes, M.H., Paik, J.: Dark channel prior-based spatially adaptive contrast enhancement for back lighting compensation. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2464–2468

  14. Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967–5976

  15. Jobson, D.J., Rahman, Zu., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997)

    Article  Google Scholar 

  16. Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision—ECCV 2016, pp. 694–711 (2016)

  17. Kim, Joung-Youn., Kim, Lee-Sup., Hwang, Seung-Ho.: An advanced contrast enhancement using partially overlapped sub-block histogram equalization. IEEE Trans. Circuits Syst. Video Technol. 11(4), 475–484 (2001)

    Article  Google Scholar 

  18. Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25

  19. Land, E.H., McCann, J.J.: Lightness and retinex theory. Josa 61(1), 1–11 (1971)

    Article  Google Scholar 

  20. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105–114

  21. Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: Aod-net: All-in-one dehazing network. In: 2017IEEE International Conference on Computer Vision (ICCV), pp. 4780–4788

  22. Li, R., Pan, J., Li, Z., Tang, J.: Single image dehazing via conditional generative adversarial network. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8202–8211

  23. LI, Tl., XIAO, J., ZHAI, Dh.: Traffic image de-haze algorithm based on adaptive parameter size. J. Southwest Univ. Sci. Technol. p 04 (2014)

  24. Lim, S.H., Mat Isa, N.A., Ooi, C.H., Toh, K.K.V.: A new histogram equalization method for digital image enhancement and brightness preservation. Signal Image Video Process. 9(3), 675–689 (2015)

    Article  Google Scholar 

  25. Liu, W., Liu, X., Ma, H., Cheng, P.: Beyond human-level license plate super-resolution with progressive vehicle search and domain priori gan. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 1618–1626 (2017)

  26. Liu, X., Liu, W., Mei, T., Ma, H.: Provid: progressive and multimodal vehicle reidentification for large-scale urban surveillance. IEEE Trans. Multimed. 20(3), 645–658 (2017b)

    Article  Google Scholar 

  27. Liu, X., Ma, Y., Shi, Z., Chen, J.: Griddehazenet: Attention-based multi-scale network for image dehazing. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7314–7323

  28. Liu, X., Zhang, M., Liu, W., Song, J., Mei, T.: Braidnet: Braiding semantics and details for accurate human parsing. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 338–346

  29. Ma, W., Xie, X., Yin, C., Lai, J.: Face image illumination processing based on generative adversarial nets. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2558–2563 (2018)

  30. Mei, K., Jiang, A., Li, J., Mingwen, W.: Progressive feature fusion network for realistic image dehazing. In: Asian Conference on Computer Vision, pp. 203–215

  31. Okuno, T., Nishitani, T.: Efficient multi-scale retinex algorithm using multi-rate image processing. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 3145–3148 (2009)

  32. Qin, X., Wang, Z., Bai, Y., Xie, X., Jia, H.: Ffa-net: feature fusion attention network for single image dehazing. Proc. AAAI Conf. Artif. Intell. 34, 11908–11915 (2020)

    Google Scholar 

  33. Qu, Y., Chen, Y., Huang, J., Xie, Y.: Enhanced pix2pix dehazing network. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8152–8160 (2019)

  34. Rahman, Zu., Jobson, D.J., Woodell, G.A.: Retinex processing for automatic image enhancement. J. Electron. Imaging 13(1), 100–110 (2004)

    Article  Google Scholar 

  35. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.H.: Single image dehazing via multi-scale convolutional neural networks. Comput. Vis. ECCV 2016, 154–169 (2016)

    Google Scholar 

  36. Romano, Y., Elad, M.: Sos boosting of image denoising algorithms. arXiv:1502.06220 (2015)

  37. Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234–241 (2015)

  38. Santra, S., Mondal, R., Chanda, B.: Learning a patch quality comparator for single image dehazing. IEEE Trans. Image Process. 27(9), 4598–4607 (2018)

    Article  MathSciNet  Google Scholar 

  39. Singh, K., Kapoor, R.: Image enhancement using exposure based sub image histogram equalization. Pattern Recognit. Lett. 36, 10–14 (2014)

    Article  Google Scholar 

  40. Singh, K., Kapoor, R., Sinha, S.K.: Enhancement of low exposure images via recursive histogram equalization algorithms. Optik Int. J. Light Electron Opt. 126(20), 2619–2625 (2015)

    Article  Google Scholar 

  41. Sreenivasan, K., Havlicek, M., Deshpande, G.: Non-parametric hemodynamic deconvolution of FMRI using homomorphic filtering. IEEE Trans Med. Imaging 34(5), 1155–1163 (2014)

    Article  Google Scholar 

  42. Tang, K., Yang, J., Wang, J.: Investigating haze-relevant features in a learning framework for image dehazing. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2995–3002 (2014)

  43. Tirandaz, Z., Akbarizadeh, G.: A two-phase algorithm based on kurtosis curvelet energy and unsupervised spectral regression for segmentation of SAR images. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 9(3), 1244–1264 (2015)

    Article  Google Scholar 

  44. Tirandaz, Z., Akbarizadeh, G., Kaabi, H.: Polsar image segmentation based on feature extraction and data compression using weighted neighborhood filter bank and hidden markov random field-expectation maximization. Measurement 153, 107432 (2020)

    Article  Google Scholar 

  45. Ulyanov, D., Vedaldi, A., Lempitsky, VS.: Instance normalization: the missing ingredient for fast stylization. CoRR abs/1607.08022, arXiv:1607.08022 (2016)

  46. Wu, S., Hu, Z., Yu, W., Feng, J.: An improved image enhancement approach based on retinex theory. In: 2013 International Conference on Information Technology and Applications, pp. 67–71 (2013)

  47. Xiao, L., Li, C., Wu, Z., Wang, T.: An enhancement method for X-ray image via fuzzy noise removal and homomorphic filtering. Neurocomputing 195, 56–64 (2016)

    Article  Google Scholar 

  48. Yang, D., Sun, J.: Proximal dehaze-net: A prior learning-based deep network for single image dehazing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds) Computer Vision—ECCV 2018, pp. 729–746 (2018)

  49. Zalpour, M., Akbarizadeh, G., Alaei-Sheini, N.: A new approach for oil tank detection using deep learning features with control false alarm rate in high-resolution satellite imagery. Int. J. Remote Sens. 41(6), 2239–2262 (2020)

    Article  Google Scholar 

  50. Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3194–3203 (2018)

  51. Zhang, H., Sindagi, V., Patel, V.M.: Joint transmission map estimation and dehazing using deep networks. IEEE Trans. Circuits Syst. Video Technol. 30(7), 1975–1986 (2020)

    Google Scholar 

  52. Zhang, X.C., Jin, X.D.: Computer vision and digital image processing in intelligent navigation system. Appl. Mech. Mater. 687, 3828–3831 (2014)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by National Natural Science Foundation of China (Grant No.617 03337), and by Aviation Science Foundation of China (Grant No.ASFC-20191053002).

Author information

Authors and Affiliations

  1. School of Astronautics, Northwestern Polytechnical University, No. 127 Youyi West Road, Xi’an, 710072, China

    Shaoyi Li & Xi Yang

  2. Unmanned System Technology Research Institute, Northwestern Polytechnical University, No. 127 Youyi West Road, Xi’an, 710072, China

    Jian Lin

  3. Xi’an Modern Control Technology Research Institute, No. 10 Zhangba East Road, Xi’an, 710065, China

    Jun Ma

  4. China Airborne Missile Academy, No. 166 Jiefang Road, Luoyang, 471000, China

    Yifeng Chen

Authors
  1. Shaoyi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jian Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xi Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yifeng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shaoyi Li.

Ethics declarations

Conflict of interest

We 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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, S., Lin, J., Yang, X. et al. BPFD-Net: enhanced dehazing model based on Pix2pix framework for single image. Machine Vision and Applications 32, 124 (2021). https://doi.org/10.1007/s00138-021-01248-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-021-01248-9

Keywords

Search

Navigation