Two-Phase Transmission Map Estimation for Robust Image Dehazing

  • Qiaoling Shu
  • Chuansheng Wu
  • Ryan Wen Liu
  • Kwok Tai Chui
  • Shengwu Xiong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)


A robust two-phase transmission map estimation framework is proposed in this paper for single image dehazing. The proposed framework first estimates the coarse transmission map through the statistical assumption of dark channel prior (DCP). To refine the coarse transmission map, a novel image-gradient-guided high-order variational method is then proposed in the second phase. The resulting L1-regularized high-order nonsmooth optimization problem will be effectively solved using the primal-dual algorithm. Once the fine transmission map is accurately obtained, the final haze-free image could be restored based on the haze imaging model of Koschmieder. To further enhance dehazing performance, an improved tolerance mechanism is incorporated into the proposed method to suppress the undesirable artifacts usually produced by DCP in large sky regions. Numerous experiments on both synthetic and realistic images were performed to compare our proposed method with several state-of-the-art dehazing methods. Dehazing results have illustrated the superior performance of the proposed method.


Image dehazing Image restoration Dark channel prior Total generalized variation Primal-dual algorithm 



This work was supported by the National Natural Science Foundation of China (No.: 51609195), and the Fund of Hubei Key Laboratory of Transportation Internet of Things (No.: WHUTIOT-2017B003).


  1. 1.
    Li, Y., You, S., Brown, M.S., Tan, R.T.: Haze visibility enhancement: a survey and quantitative benchmarking. Comput. Vis. Image Understand. 165, 1–16 (2017)CrossRefGoogle Scholar
  2. 2.
    Wang, W., Yuan, X.: Recent advances in image dehazing. IEEE/CAA J. Autom. Sinica 4(3), 410–436 (2017)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Ancuti, C.O., Ancuti, C.: Single image dehazing by multi-scale fusion. IEEE Trans. Image Process. 22(8), 3271–3282 (2013)CrossRefGoogle Scholar
  4. 4.
    Kim, J.H., Jang, W.D., Sim, J.Y., Kim, C.S.: Optimized contrast enhancement for real-time image and video dehazing. J. Vis. Commun. Image Represent. 24(3), 410–425 (2013)CrossRefGoogle Scholar
  5. 5.
    Fattal, R.: Dehazing using color-lines. ACM Trans. Graph. 34(1), 13 (2014)CrossRefGoogle Scholar
  6. 6.
    Ono, S., Yamada, I.: Color-line regularization for color artifact removal. IEEE Trans. Comput. Imaging 2(3), 204–217 (2016)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Berman, D., Treibitz, T., Avidan, S.: Non-local image dehazing. In: IEEE CVPR, pp. 1674–1682 (2016)Google Scholar
  8. 8.
    Berman, D., Treibitz, T., Avidan, S.: Air-light estimation using haze-lines. In: IEEE ICCP, pp. 1–9 (2017)Google Scholar
  9. 9.
    Fattal, R.: Single image dehazing. ACM Trans. Graph. 27(3), 72 (2008)CrossRefGoogle Scholar
  10. 10.
    He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Patt. Anal. Mach. Int. 33(12), 2341–2353 (2011)CrossRefGoogle Scholar
  11. 11.
    Gibson, K.B., Vo, D.T., Nguyen, T.Q.: An investigation of dehazing effects on image and video coding. IEEE Trans. Image Process. 21(2), 662–673 (2012)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Tripathi, A.K., Mukhopadhyay, S.: Single image fog removal using anisotropic diffusion. IET Image Process. 6(7), 966–975 (2012)MathSciNetCrossRefGoogle Scholar
  13. 13.
    He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Patt. Anal. Mach. Int. 35(6), 1397–1409 (2013)CrossRefGoogle Scholar
  14. 14.
    Li, Z., Zheng, J., Zhu, Z., Yao, W., Wu, S.: Weighted guided image filtering. IEEE Trans. Image Process. 24(1), 120–129 (2015)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Li, Z., Zheng, J.: Edge-preserving decomposition-based single image haze removal. IEEE Trans. Image Process. 24(12), 5432–5441 (2015)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Li, L., Feng, W., Zhang, J.: Contrast enhancement based single image dehazing via TV-L1 minimization. In: IEEE ICME, pp. 1–6 (2014)Google Scholar
  17. 17.
    Fang, F., Li, F., Zeng, T.: Single image dehazing and denoising: a fast variational approach. SIAM J. Imaging Sci. 7(2), 969–996 (2014)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Liu, R.W., Xiong, S., Wu, H.: A second-order variational framework for joint depth map estimation and image dehazing. In: IEEE ICASSP, pp. 1433–1437 (2018)Google Scholar
  19. 19.
    Wang, W., Yuan, X., Wu, X., Liu, Y.: Dehazing for images with large sky region. Neurocomputing 238, 365–376 (2017)CrossRefGoogle Scholar
  20. 20.
    Gao, Y., Hu, H.M., Wang, S., Li, B.: A fast image dehazing algorithm based on negative correction. Signal Process. 103, 380–398 (2014)CrossRefGoogle Scholar
  21. 21.
    Liu, Y., Li, H., Wang, M.: Single image dehazing via large sky region segmentation and multiscale opening dark channel model. IEEE Access 5, 8890–8903 (2017)CrossRefGoogle Scholar
  22. 22.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  23. 23.
    Ancuti, C., Ancuti, C.O., Timofte, R., et al.: NTIRE 2018 challenge on image dehazing: methods and results. In: CVPR, pp. 1004–1014 (2018)Google Scholar
  24. 24.
    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)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.-H.: Single image dehazing via multi-scale convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 154–169. Springer, Cham (2016). Scholar
  26. 26.
    Li, B., Peng, X., Wang, Z., Xu, J., Feng, D.: AOD-Net: All-in-one dehazing network. In: ICCV, pp. 4770–4778 (2017)Google Scholar
  27. 27.
    Zhang, H., Sindagi, V., Patel, V.M.: Multi-scale single image dehazing using perceptual pyramid deep network. In: CVPR, pp. 902–911 (2018)Google Scholar
  28. 28.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: NIPS, pp. 2672–268 (2014)Google Scholar
  29. 29.
    Li, R., Pan, J., Li, Z., Tang, J.: Single image dehazing via conditional generative adversarial network. In: CVPR, pp. 8202–8211 (2018)Google Scholar
  30. 30.
    Tan, R.: Visibility in bad weather from a single image. In: CVPR, pp. 1–8 (2008)Google Scholar
  31. 31.
    Tarel, J.P., Hautiere, N.: Fast visibility restoration from a single color or gray level image. In: ICCV, pp. 2201–2208 (2009)Google Scholar
  32. 32.
    Bredies, K., Kunisch, K., Pock, T.: Total generalized variation. SIAM J. Imaging Sci. 3(3), 492–526 (2010)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Liu, R.W., Shi, L., Yu, C.H., Wang, D.: Box-constrained second-order total generalized variation minimization with a combined L1,2 data-fidelity term for image reconstruction. J. Electron. Imaging 24(3), 033026 (2015)CrossRefGoogle Scholar
  34. 34.
    Liu, R.W., Shi, L., Huang, W., Xu, J., Yu, C.H., Wang, D.: Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters. Magn. Reson. Imaging 32(6), 702–720 (2014)CrossRefGoogle Scholar
  35. 35.
    Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vision 40(1), 120–145 (2011)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Condat, L.: A primal-dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms. J. Optimiz. Theor. Appl. 158(2), 460–479 (2013)MathSciNetCrossRefGoogle Scholar
  37. 37.
    Lu, W., Duan, J., Qiu, Z., Pan, Z., Liu, R.W., Bai, L.: Implementation of high-order variational models made easy for image processing. Math. Methods Appl. Sci. 39(14), 4208–4233 (2016)MathSciNetCrossRefGoogle Scholar
  38. 38.
    Meng, G., Wang, Y., Duan, J., Xiang, S., Pan, C.: Efficient image dehazing with boundary constraint and contextual regularization. In: ICCV, pp. 617–624 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Qiaoling Shu
    • 1
  • Chuansheng Wu
    • 1
  • Ryan Wen Liu
    • 2
    • 3
  • Kwok Tai Chui
    • 4
  • Shengwu Xiong
    • 3
  1. 1.Department of MathematicsWuhan University of TechnologyWuhanChina
  2. 2.School of NavigationWuhan University of TechnologyWuhanChina
  3. 3.Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and TechnologyWuhan University of TechnologyWuhanChina
  4. 4.Department of Electronic EngineeringCity University of Hong KongKowloon TongHong Kong

Personalised recommendations