Blind Space-Variant Single-Image Restoration of Defocus Blur

  • Leah BarEmail author
  • Nir Sochen
  • Nahum Kiryati
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10302)


We address the problem of blind piecewise space-variant image deblurring where only part of the image is sharp, assuming a shallow depth of field which imposes significant defocus blur.

We propose an automatic image recovery approach which segments the sharp and blurred sub-regions, iteratively estimates a non-parametric blur kernel and restores the sharp image via a variational non-blind space variant method.

We present a simple and efficient blur measure which emphasizes the blur difference of the sub-regions followed by a blur segmentation procedure based on an evolving level set function.

One of the contributions of this work is the extension to the space-variant case of progressive blind deconvolution recently proposed, an iterative process consisting of non-parametric blind kernel estimation and residual blur deblurring. Apparently this progressive strategy is superior to the one step deconvolution procedure. Experimental results on real images demonstrate the effectiveness of the proposed algorithm.


Space-variant deblurring Blind deconvolution Blur segmentation 


  1. 1.
    Bae, S., Durand, F.: Defocus magnification. In: EUROGRAPHICS (2007)Google Scholar
  2. 2.
    Bar, L., Sochen, N., Kiryati, N.: Restoration of images with piecewise space-variant blur. In: Sgallari, F., Murli, A., Paragios, N. (eds.) SSVM 2007. LNCS, vol. 4485, pp. 533–544. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-72823-8_46 CrossRefGoogle Scholar
  3. 3.
    Braides, A.: Approximation of Free-Discontinuity Problems. LNM, vol. 1694. Springer, Heidelberg (1998)CrossRefzbMATHGoogle Scholar
  4. 4.
    Cao, Y., Fang, S., Wang, Z.: Digital multi-focusing from a single photograph taken with an uncalibrated conventional camera. IEEE Trans. Image Process. 22, 3703–3714 (2013)CrossRefGoogle Scholar
  5. 5.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22, 61–79 (1997)CrossRefzbMATHGoogle Scholar
  6. 6.
    Chakrabarti, A., Zickler, T., Freeman, W.T.: Analyzing spatially-varying blur. In: CVPR (2010)Google Scholar
  7. 7.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Process. 10, 266–277 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Frommer, Y., Ben-Ari, R., Kiryati, N.: Adaptive shape from focus based on high order derivatives. In: Proceedings of the 26th British Machine Vision Conference (BMVC 2015) (2015)Google Scholar
  9. 9.
    Hanocka, R., Kiryati, N.: Progressive blind deconvolution. In: Azzopardi, G., Petkov, N. (eds.) CAIP 2015. LNCS, vol. 9257, pp. 313–325. Springer, Cham (2015). doi: 10.1007/978-3-319-23117-4_27 CrossRefGoogle Scholar
  10. 10.
    Javaran, T.A., Hassanpour, H., Abolghasemi, V.: Automatic estimation and segmentation of partial blur in natural images. Vis. Comput. 33, 151–161 (2017). doi: 10.1007/s00371-015-1166-z CrossRefGoogle Scholar
  11. 11.
    Kimmel, R.: Fase edge integration. In: Osher, S., Paragios, N. (eds.) Geometric Level Set Methods in Imaging Vision and Graphics. Springer, New York (2003)Google Scholar
  12. 12.
    Komodakis, N., Paragios, N.: MRF-based blind image deconvolution. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7726, pp. 361–374. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-37431-9_28 CrossRefGoogle Scholar
  13. 13.
    Kotera, J., Šroubek, F., Milanfar, P.: Blind deconvolution using alternating maximum a posteriori estimation with heavy-tailed priors. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds.) CAIP 2013. LNCS, vol. 8048, pp. 59–66. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40246-3_8 CrossRefGoogle Scholar
  14. 14.
    Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR (2011)Google Scholar
  15. 15.
    Lai, W.S., Huang, J.B., Hu, Z., Ahuja, A., Yang, M.H.: A comparative study for single image blind deblurring. In: CVPR (2016)Google Scholar
  16. 16.
    Levin, A.: Blind motion deblurring using image statistics. In: Advances in Neural Information Processing Systems (NIPS 2006) (2006)Google Scholar
  17. 17.
    Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR (2011)Google Scholar
  18. 18.
    Liu, S., Zhou, F., Liao, Q.: Defocus map estimation from a single image based on two-parameter defocus model. IEEE Trans. Image Process. 25, 5943–5956 (2016)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Loktyushin, A., Harmeling, S.: Automatic foreground-background refocusing. In: ICIP (2011)Google Scholar
  20. 20.
    Mahmoudpour, S., Kim, M.: Superpixel-based depth map estimation using defocus blur. In: ICIP (2016)Google Scholar
  21. 21.
    Marshall, J.A., Burbeck, C.A., Arieli, D., Rolland, J.P., Martin, K.E.: Occlusion edge blur: a cue to relative visual depth. J. Opt. Soc. Am. A 13, 681–688 (1996)CrossRefGoogle Scholar
  22. 22.
    Nayar, S.K., Nakagawa, Y.: Shape from focus. IEEE Trans. Pattern Anal. Mach. Intell. 16(8), 824–831 (1994)CrossRefGoogle Scholar
  23. 23.
    Pan, J., Hu, Z., Su, Z., Lee, H.Y., Yang, M.H.: Soft-segmentation guided object motion deblurring. In: CVPR (2016)Google Scholar
  24. 24.
    Pang, Y., Zhu, H., Li, X., Pan, J.: Motion blur detection with an indicator function for surveillance machines. IEEE Trans. Ind. Electron. 63, 5592–5601 (2016)CrossRefGoogle Scholar
  25. 25.
    Schelten, K., Roth, S.: Localized image blur removal through non-parametric kernel estimation. In: ICPR (2014)Google Scholar
  26. 26.
    Tiwari, J., Rai, R.K., Shrman, B.: A review on estimation of defocus blur from a single image. Int. J. Comput. Appl. 106, 0975–8887 (2014)Google Scholar
  27. 27.
    Zhang, W., Cham, W.: Single-image refocusing and defocusing. IEEE Trans. Image Process. 21, 873–882 (2012)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Zhang, Y., Hirakawa, K.: Blind deblurring and denoising of images corrupted by unidirectional object motion blur and sensor noise. IEEE Trans. Image Process. 25, 4129–4144 (2016)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Zhu, X., Cohen, S., Schiller, S., Milanfar, P.: Estimating spatially varying defocus blur from a single image. IEEE Trans. Image Process. 22, 4879–4891 (2013)MathSciNetCrossRefGoogle Scholar
  30. 30.
    Zon, N., Hanocka, R., Kiryati, N.: Fast and easy blind deblurring using an inverse filter and probe (2017). arXiv:1702.01315

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Applied MathematicsTel-Aviv UniversityTel-avivIsrael
  2. 2.School of Electrical EngineeringTel-Aviv UniversityTel-avivIsrael

Personalised recommendations