Skip to main content
SpringerLink
Log in

Single Image Dehazing with Deep-Image-Prior Networks

  • Conference paper
  • First Online:
Image and Graphics (ICIG 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14357))

Included in the following conference series:

  • 364 Accesses

Abstract

Most conventional dehazing methods focus on separately estimating key parameters (e.g., the transmission map and the atmospheric light) based on the atmospheric scattering model to generate haze-free images, which may face the limitation of error accumulation. With the advance of deep learning technologies, employing deep neural networks (DNNs) to conduct haze removal becomes popular dehazing methods recently. Most DNNs-based methods automatically learn haze-free image or key parameters in the atmospheric scattering model in end-to-end manners, which heavily rely on training models on dataset. This work aims to recover haze-free images directly by DNNs without any time-consuming training process on dataset or cascading parameter estimation steps. In this paper, haze removal is achieved in Maximum-a-Posterior (MAP) framework based on an exist re-formulation of the atmospheric scattering model, which only involves one integrated variable. The proposed MAP framework is connected with DNN by two self-supervised generative networks—two deep-image-prior (DIP) networks, which are present for modeling the deep priors of the haze-free image and the integrated variable. We further investigate the statistical property of the integrated variable and propose handcrafted regularizers to better constrain the integrated variable. By iteratively updating two networks, solutions of the haze-free image and the integrated variable can be solved jointly. Experiments on both synthesized and real hazy images show that the proposed method performs competitively to state-of-the-art dehazing methods in terms of PSNR, SSIM and visual evaluations.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Berman, D., Treibitz, T., Avidan, S.: Non-local image dehazing. In: Computer Vision and Pattern Recognition, pp. 1674–1682 (2016). https://doi.org/10.1109/CVPR.2016.185

  2. 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). https://doi.org/10.1109/TIP.2016.2598681

    Article  MathSciNet  MATH  Google Scholar 

  3. Engin, D., Genç, A., Ekenel, H.K.: Cycle-dehaze: enhanced CycleGAN for single image dehazing. In: Computer Vision and Pattern Recognition Workshops, pp. 825–833 (2018). https://doi.org/10.1109/CVPRW.2018.00127

  4. Fattal, R.: Single image dehazing. ACM Trans. Graphics 27(3), 72 (2008). https://doi.org/10.1145/1360612.1360671

    Article  Google Scholar 

  5. Fattal, R.: Dehazing using color-lines. ACM Trans. Graphics 34(1), 13:1–13:14 (2014). https://doi.org/10.1145/2651362

  6. Gandelsman, Y., Shocher, A., Irani, M.: “Double-DIP": unsupervised image decomposition via coupled deep-image-priors. In: Computer Vision and Pattern Recognition, pp. 11026–11035 (2019). https://doi.org/10.1109/CVPR.2019.01128

  7. Guo, C., Yan, Q., Anwar, S., Cong, R., Ren, W., Li, C.: Image dehazing transformer with transmission-aware 3d position embedding. In: Computer Vision and Pattern Recognition, pp. 5802–5810 (2022). https://doi.org/10.1109/CVPR52688.2022.00572

  8. 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). https://doi.org/10.1109/TPAMI.2010.168

    Article  Google Scholar 

  9. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015), arxiv.org/abs/1412.6980

  10. Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: AOD-Net: all-in-one dehazing network. In: International Conference on Computer Vision. pp. 4780–4788 (2017). https://doi.org/10.1109/ICCV.2017.511

  11. Li, B., et al.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492–505 (2019). https://doi.org/10.1109/TIP.2018.2867951

    Article  MathSciNet  MATH  Google Scholar 

  12. Li, R., Pan, J., Li, Z., Tang, J.: Single image dehazing via conditional generative adversarial network. In: Computer Vision and Pattern Recognition, pp. 8202–8211 (2018). https://doi.org/10.1109/CVPR.2018.00856

  13. Liu, W., Hou, X., Duan, J., Qiu, G.: End-to-end single image fog removal using enhanced cycle consistent adversarial networks. IEEE Trans. Image Process. 29, 7819–7833 (2020). https://doi.org/10.1109/TIP.2020.3007844

    Article  MATH  Google Scholar 

  14. Liu, X., Ma, Y., Shi, Z., Chen, J.: GridDehazeNet: attention-based multi-scale network for image dehazing. In: International Conference on Computer Vision, pp. 7313–7322 (2019). https://doi.org/10.1109/ICCV.2019.00741

  15. McCartney, E.J.: Optics of the atmosphere: Scattering by molecules and particles 1 (1976)

    Google Scholar 

  16. Meng, G., Wang, Y., Duan, J., Xiang, S., Pan, C.: Efficient image dehazing with boundary constraint and contextual regularization. In: International Conference on Computer Vision, pp. 617–624 (2013). https://doi.org/10.1109/ICCV.2013.82

  17. Narasimhan, S.G., Nayar, S.K.: Contrast restoration of weather degraded images. IEEE Trans. Pattern Anal. Mach. Intell. 25(6), 713–724 (2003). https://doi.org/10.1109/TPAMI.2003.1201821

    Article  Google Scholar 

  18. Pan, J., et al.: Learning dual convolutional neural networks for low-level vision. In: Computer Vision and Pattern Recognition, pp. 3070–3079 (2018). https://doi.org/10.1109/CVPR.2018.00324

  19. Paszke, A., et al.: Automatic differentiation in pytorch. In: Neural Information Processing Systems Autodiff Workshop (2017). https://openreview.net/pdf?id=BJJsrmfCZ

  20. Qu, Y., Chen, Y., Huang, J., Xie, Y.: Enhanced pix2pix dehazing network. In: Computer Vision and Pattern Recognition, pp. 8160–8168 (2019). https://doi.org/10.1109/CVPR.2019.00835

  21. Ren, D., Zhang, K., Wang, Q., Hu, Q., Zuo, W.: Neural blind deconvolution using deep priors. In: Computer Vision and Pattern Recognition, pp. 3338–3347 (2020). https://doi.org/10.1109/CVPR42600.2020.00340

  22. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.: Single image dehazing via multi-scale convolutional neural networks. In: European Conference on Computer Vision, pp. 154–169 (2016). https://doi.org/10.1007/978-3-319-46475-6_10

  23. Ren, W., et al.: Gated fusion network for single image dehazing. In: Computer Vision and Pattern Recognition, pp. 3253–3261 (2018). https://doi.org/10.1109/CVPR.2018.00343

  24. Schechner, Y.Y., Narasimhan, S.G., Nayar, S.K.: Instant dehazing of images using polarization. In: Computer Vision and Pattern Recognition, pp. 325–332 (2001). https://doi.org/10.1109/CVPR.2001.990493

  25. Shwartz, S., Namer, E., Schechner, Y.Y.: Blind haze separation. In: Computer Vision and Pattern Recognition, pp. 1984–1991 (2006). https://doi.org/10.1109/CVPR.2006.71

  26. Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision, pp. 746–760 (2012). https://doi.org/10.1007/978-3-642-33715-4_54

  27. Stark, J.A.: Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Trans. Image Process. 9(5), 889–896 (2000). https://doi.org/10.1109/83.841534

    Article  Google Scholar 

  28. Tan, R.T.: Visibility in bad weather from a single image. In: Computer Vision and Pattern Recognition (2008). https://doi.org/10.1109/CVPR.2008.4587643

  29. Ulyanov, D., Vedaldi, A., Lempitsky, V.S.: Deep image prior. Int. J. Comput. Vision 128(7), 1867–1888 (2020). https://doi.org/10.1007/s11263-020-01303-4

    Article  Google Scholar 

  30. Yang, X., Xu, Z., Luo, J.: Towards perceptual image dehazing by physics-based disentanglement and adversarial training. In: Association for the Advancement of Artificial Intelligence, pp. 7485–7492 (2018)

    Google Scholar 

  31. Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: Computer Vision and Pattern Recognition, pp. 3194–3203 (2018). https://doi.org/10.1109/CVPR.2018.00337

  32. Zhang, H., Sindagi, V., Patel, V.M.: Multi-scale single image dehazing using perceptual pyramid deep network. In: Computer Vision and Pattern Recognition Workshops, pp. 902–911 (2018). https://doi.org/10.1109/CVPRW.2018.00135

  33. Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522–3533 (2015). https://doi.org/10.1109/TIP.2015.2446191

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

This work has been partially supported by National Natural Science Foundation of China (No. 61976041).

Author information

Authors and Affiliations

  1. Dalian University of Foreign Language, Dalian, China

    Hongyan Wang

  2. Beijing Huawei Digital Technologies Co., Ltd., Beijing, China

    Xin Wang

  3. Dalian University of Technology, Dalian, China

    Zhixun Su

Authors
  1. Hongyan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhixun Su
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hongyan Wang .

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Huchuan Lu

  2. University of Sydney, Sydney, NSW, Australia

    Wanli Ouyang

  3. Shenzhen University, Shenzhen, China

    Hui Huang

  4. Tsinghua University, Beijing, China

    Jiwen Lu

  5. Dalian University of Technology, Dalian, China

    Risheng Liu

  6. Institute of Automation, CAS, Beijing, China

    Jing Dong

  7. University of Technology Sydney, Sydney, NSW, Australia

    Min Xu

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, H., Wang, X., Su, Z. (2023). Single Image Dehazing with Deep-Image-Prior Networks. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14357. Springer, Cham. https://doi.org/10.1007/978-3-031-46311-2_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-46311-2_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-46310-5

  • Online ISBN: 978-3-031-46311-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation