Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields

Incheol Kim, Min H. Kim

Abstract

Removing haze from a single image is a severely ill-posed problem due to the lack of the scene information. General dehazing algorithms estimate airlight initially using natural image statistics and then propagate the incompletely estimated airlight to build a dense transmission map, yielding a haze-free image. Propagating haze is different from other regularization problems, as haze is strongly correlated with depth according to the physics of light transport in participating media. However, since there is no depth information available in single-image dehazing, traditional regularization methods with a common grid random field often suffer from haze isolation artifacts caused by abrupt changes in scene depths. In this paper, to overcome the haze isolation problem, we propose a non-local regularization method by combining Markov random fields (MRFs) with nearest-neighbor fields (NNFs), based on our insightful observation that the NNFs searched in a hazy image associate patches at the similar depth, as local haze in the atmosphere is proportional to its depth. We validate that the proposed method can regularize haze effectively to restore a variety of natural landscape images, as demonstrated in the results. This proposed regularization method can be used separately with any other dehazing algorithms to enhance haze regularization.

References

  1. Ancuti, C. O. and Ancuti, C. (2013). Single image dehazing by multi-scale fusion. IEEE Trans. Image Processing, 22(8):3271-3282.
  2. Barnes, C., Shechtman, E., Finkelstein, A., and Goldman, D. B. (2009). Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph, 28(3):24:1-24:11.
  3. Berman, D., Treibitz, T., and Avidan, S. (2016). Non-local image dehazing. In IEEE CVPR, pages 1674-1682.
  4. Besse, F., Rother, C., Fitzgibbon, A. W., and Kautz, J. (2014). PMBP: Patchmatch belief propagation for correspondence field estimation. International Journal of Computer Vision, 110(1):2-13.
  5. Carr, P. and Hartley, R. I. (2009). Improved single image dehazing using geometry. In DICTA 2009, pages 103- 110.
  6. Fattal, R. (2008). Single image dehazing. ACM Trans. Graph., 27(3):72:1-72:9.
  7. Fattal, R. (2014). Dehazing using color-lines. ACM Trans. Graph., 34(1):13:1-13:14.
  8. He, K., Sun, J., and Tang, X. (2013). Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell., 35(6):1397- 1409.
  9. He, K. M., Sun, J., and Tang, X. (2009). Single image haze removal using dark channel prior. In Proc. IEEE CVPR, pages 1956-1963.
  10. Kim, M. H. and Kautz, J. (2008). Consistent tone reproduction. In Proc. the IASTED International Conference on Computer Graphics and Imaging (CGIM 2008), pages 152-159, Innsbruck, Austria. IASTED/ACTA Press.
  11. Kim, M. H. and Kautz, J. (2009). Consistent scene illumination using a chromatic flash. In Proc. Eurographics Workshop on Computational Aesthetics (CAe2009), pages 83-89, British Columbia, Canada. Eurographics.
  12. Kopf, J., Neubert, B., Chen, B., Cohen, M. F., CohenOr, D., Deussen, O., Uyttendaele, M., and Lischinski, D. (2008). Deep photo: model-based photograph enhancement and viewing. ACM Trans. Graph., 27(5):116:1-116:10.
  13. Levin, A., Lischinski, D., and Weiss, Y. (2008). A closedform solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell., 30(2):228-242.
  14. Li, Y., Tan, R. T., and Brown, M. S. (2015). Nighttime haze removal with glow and multiple light colors. In 2015 IEEE ICCV 2015, Santiago, Chile, December 7-13, 2015, pages 226-234.
  15. Li, Y. P. and Huttenlocher, D. P. (2008). Sparse long-range random field and its application to image denoising. In ECCV, pages III: 344-357.
  16. Marroquín, J. L., Velasco, F. A., Rivera, M., and Nakamura, M. (2001). Gauss-markov measure field models for low-level vision. IEEE Trans. Pattern Anal. Mach. Intell., 23(4):337-348.
  17. Meng, G., Wang, Y., Duan, J., Xiang, S., and Pan, C. (2013). Efficient image dehazing with boundary constraint and contextual regularization. In Proc. IEEE ICCV, pages 617-624.
  18. Narasimhan, S. G. and Nayar, S. K. (2002). Vision and the atmosphere. Int. Journal of Computer Vision, 48(3):233-254.
  19. Narasimhan, S. G. and Nayar, S. K. (2003). Contrast restoration of weather degraded images. IEEE Trans. Pattern Anal. Mach. Intell, 25(6):713-724.
  20. Nishino, K., Kratz, L., and Lombardi, S. (2012). Bayesian defogging. Int. Journal of Computer Vision, 98(3):263-278.
  21. Schechner, Y. Y., Narasimhan, S. G., and Nayar, S. K. (2001). Instant dehazing of images using polarization. In Proc. IEEE CVPR, pages I:325-332.
  22. Tan, R. T. (2008). Visibility in bad weather from a single image. In Proc. IEEE CVPR, pages 1-8.
  23. Tang, K., Yang, J., and Wang, J. (2014). Investigating hazerelevant features in a learning framework for image dehazing. In Proc. IEEE CVPR, pages 2995-3002.
  24. Tarel, J. and Hautière, N. (2009). Fast visibility restoration from a single color or gray level image. In Proc. IEEE ICCV, pages 2201-2208.
  25. Zhang, Q., Xu, L., and Jia, J. (2014). 100+ times faster weighted median filter (WMF). In CVPR, pages 2830-2837. IEEE.
  26. Zhu, Q., Mai, J., and Shao, L. (2015). A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Processing, 24(11):3522-3533.
Download


Paper Citation


in Harvard Style

Kim I. and H. Kim M. (2017). Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 77-88. DOI: 10.5220/0006132400770088


in Bibtex Style

@conference{visapp17,
author={Incheol Kim and Min H. Kim},
title={Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={77-88},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006132400770088},
isbn={978-989-758-225-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Dehazing using Non-local Regularization with Iso-depth Neighbor-Fields
SN - 978-989-758-225-7
AU - Kim I.
AU - H. Kim M.
PY - 2017
SP - 77
EP - 88
DO - 10.5220/0006132400770088