Non-local Haze Propagation with an Iso-Depth Prior

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 983)


The primary challenge for removing haze from a single image is lack of decomposition cues between the original light transport and airlight scattering in a scene. Many dehazing algorithms start from an assumption on natural image statistics to estimate airlight from sparse cues. The sparsely estimated airlight cues need to be propagated according to the local density of airlight in the form of a transmission map, which allows us to obtain a haze-free image by subtracting airlight from the hazy input. Traditional airlight-propagation methods rely on ordinary regularization on a grid random field, which often results in isolated haze artifacts when they fail in estimating local density of airlight properly. In this work, we propose a non-local regularization method for dehazing by combining Markov random fields (MRFs) with nearest-neighbor fields (NNFs) extracted from the hazy input using the PatchMatch algorithm. Our method starts from the insightful observation that the extracted NNFs can associate pixels at the similar depth. Since regional haze in the atmosphere is correlated with its depth, we can allow propagation across the iso-depth pixels with the MRF-based regularization problem with the NNFs. Our results validate how our method can restore a wide range of hazy images of natural landscape clearly without suffering from haze isolation artifacts. Also, our regularization method is directly applicable to various dehazing methods.


Dehazing Non-local regularization Image restoration 



Min H. Kim, the corresponding author, acknowledges Korea NRF grants (2016R1-A2B2013031, 2013M3A6A6073718) and additional support by KOCCA in MCST of Korea, Cross-Ministry Giga KOREA Project (GK17P0200), Samsung Electronics (SRFC-IT1402-02), and an ICT R&D program of MSIT/IITP of Korea (2017-0-00072, 2016-0-00018). We also would like to appreciate Seung-Hwan Baek’s helpful comments.

Supplementary material

479158_1_En_11_MOESM1_ESM.pdf (58 mb)
Supplementary material 1 (pdf 59390 KB)


  1. 1.
    Kim, I., Kim, M.H.: Dehazing using non-local regularization with Iso-depth neighbor-fields. In: Proceedings of International Conference Computer Vision, Theory and Applications (VISAPP 2017), Porto, Portugal (2017)Google Scholar
  2. 2.
    He, K.M., Sun, J., Tang, X.: Single image haze removal using dark channel prior. In: Proceedings of IEEE CVPR, pp. 1956–1963 (2009)Google Scholar
  3. 3.
    Fattal, R.: Single image dehazing. ACM Trans. Graph. 27, 72:1–72:9 (2008)CrossRefGoogle Scholar
  4. 4.
    Fattal, R.: Dehazing using color-lines. ACM Trans. Graph. 34, 13:1–13:14 (2014)CrossRefGoogle Scholar
  5. 5.
    Berman, D., Treibitz, T., Avidan, S.: Non-local image dehazing. In: IEEE CVPR, pp. 1674–1682 (2016)Google Scholar
  6. 6.
    Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28, 24:1–24:11 (2009)CrossRefGoogle Scholar
  7. 7.
    Narasimhan, S.G., Nayar, S.K.: Vision and the atmosphere. Int. J. Comput. Vis. 48, 233–254 (2002)CrossRefGoogle Scholar
  8. 8.
    Schechner, Y.Y., Narasimhan, S.G., Nayar, S.K.: Instant dehazing of images using polarization. In: Proceedings of IEEE CVPR, pp. I:325–I:332 (2001)Google Scholar
  9. 9.
    Narasimhan, S.G., Nayar, S.K.: Contrast restoration of weather degraded images. IEEE Trans. Pattern Anal. Mach. Intell. 25, 713–724 (2003)CrossRefGoogle Scholar
  10. 10.
    Kopf, J., et al.: Deep photo: model-based photograph enhancement and viewing. ACM Trans. Graph. 27, 116:1–116:10 (2008)CrossRefGoogle Scholar
  11. 11.
    Tang, K., Yang, J., Wang, J.: Investigating haze-relevant features in a learning framework for image dehazing. In: Proceedings of IEEE CVPR, pp. 2995–3002 (2014)Google Scholar
  12. 12.
    Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24, 3522–3533 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Tan, R.T.: Visibility in bad weather from a single image. In: Proceedings of IEEE CVPR, pp. 1–8 (2008)Google Scholar
  14. 14.
    Tarel, J., Hautière, N.: Fast visibility restoration from a single color or gray level image. In: Proceedings of IEEE ICCV, pp. 2201–2208 (2009)Google Scholar
  15. 15.
    Nishino, K., Kratz, L., Lombardi, S.: Bayesian defogging. Int. J. Comput. Vis. 98, 263–278 (2012)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Ancuti, C.O., Ancuti, C.: Single image dehazing by multi-scale fusion. IEEE Trans. Image Process. 22, 3271–3282 (2013)CrossRefGoogle Scholar
  17. 17.
    Li, Y., Tan, R.T., Brown, M.S.: Nighttime haze removal with glow and multiple light colors. In: 2015 IEEE ICCV 2015, Santiago, Chile, 7–13 December 2015, pp. 226–234 (2015)Google Scholar
  18. 18.
    Meng, G., Wang, Y., Duan, J., Xiang, S., Pan, C.: Efficient image dehazing with boundary constraint and contextual regularization. In: Proceedings of IEEE ICCV, pp. 617–624 (2013)Google Scholar
  19. 19.
    Carr, P., Hartley, R.I.: Improved single image dehazing using geometry. In: DICTA 2009, pp. 103–110 (2009)Google Scholar
  20. 20.
    He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1397–1409 (2013)CrossRefGoogle Scholar
  21. 21.
    Marroquín, J.L., Velasco, F.A., Rivera, M., Nakamura, M.: Gauss-Markov measure field models for low-level vision. IEEE Trans. Pattern Anal. Mach. Intell. 23, 337–348 (2001)CrossRefGoogle Scholar
  22. 22.
    Li, Y.P., Huttenlocher, D.P.: Sparse long-range random field and its application to image denoising. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 344–357. Springer, Heidelberg (2008). Scholar
  23. 23.
    Zhang, Q., Xu, L., Jia, J.: 100+ times faster weighted median filter (WMF). In: CVPR, pp. 2830–2837. IEEE (2014)Google Scholar
  24. 24.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30, 228–242 (2008)CrossRefGoogle Scholar
  25. 25.
    Kim, M.H., Kautz, J.: Consistent tone reproduction. In: Proceedings of the IASTED International Conference on Computer Graphics and Imaging (CGIM 2008), Innsbruck, Austria, pp. 152–159. IASTED/ACTA Press (2008)Google Scholar
  26. 26.
    Kim, M.H., Kautz, J.: Consistent scene illumination using a chromatic flash. In: Proceedings of Eurographics Workshop on Computational Aesthetics (CAe 2009), British Columbia, Canada, Eurographics, pp. 83–89 (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.KAISTDaejeonKorea

Personalised recommendations