Defocus Inpainting

  • Paolo Favaro
  • Enrico Grisan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


In this paper, we propose a method to restore a single image affected by space-varying blur. The main novelty of our method is the use of recurring patterns as regularization during the restoration process. We postulate that restored patterns in the deblurred image should resemble other sharp details in the input image. To this purpose, we establish the correspondence of regions that are similar up to Gaussian blur. When two regions are in correspondence, one can perform deblurring by using the sharpest of the two as a proposal. Our solution consists of two steps: First, estimate correspondence of similar patches and their relative amount of blurring; second, restore the input image by imposing the similarity of such recurring patterns as a prior. Our approach has been successfully tested on both real and synthetic data.


Input Image Point Spread Function Image Restoration Deblurred Image Corneal Imaging 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 1167–1183 (2002)CrossRefGoogle Scholar
  2. 2.
    Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: CVPR 2003, vol. II, pp. 721–728 (2003)Google Scholar
  3. 3.
    Katsaggelos, A.: Digital Image Restoration (Book). Springer, Heidelberg (1991)CrossRefGoogle Scholar
  4. 4.
    Yitzhaky, Y., Milberg, R., Yohaev, S., Kopeika, N.S.: Comparison of direct blind deconvolution methods for motion-blurred images. In: Applied Optics-IP, July 1999, vol. 38, pp. 4325–4332 (1999)Google Scholar
  5. 5.
    Bertero, M., Boccacci, P.: Introduction to inverse problems in imaging. Institute of Physics Publishing, Bristol and Philadelphia (1998)CrossRefzbMATHGoogle Scholar
  6. 6.
    Engl, H., Hanke, M., Neubauer, A.: Regularization of Inverse Problems. Kluwer Academic Publishers, Dordrecht (1996)CrossRefzbMATHGoogle Scholar
  7. 7.
    You, Y., Kaveh, M.: Blind image restoration by anisotropic diffusion. IEEE Trans. on Image Processing 8, 396–407 (1999)CrossRefGoogle Scholar
  8. 8.
    Aloimonos, Y., Swain, M.: Shape from texture. BioCyber 58, 345–360 (1988)zbMATHGoogle Scholar
  9. 9.
    Blostein, D., Ahuja, N.: Shape from texture: Integrating texture-element extraction and surface estimation. PAMI 11, 1233–1251 (1989)CrossRefGoogle Scholar
  10. 10.
    Ens, J., Lawrence, P.: An investigation of methods for determining depth from focus. IEEE Trans. Pattern Anal. Mach. Intell. 15, 97–108 (1993)CrossRefGoogle Scholar
  11. 11.
    Pentland, A.: A new sense for depth of field. IEEE Trans. Pattern Anal. Mach. Intell. 9, 523–531 (1987)CrossRefGoogle Scholar
  12. 12.
    Subbarao, M., Surya, G.: Depth from defocus: a spatial domain approach. Intl. J. of Computer Vision 13, 271–294 (1994)CrossRefGoogle Scholar
  13. 13.
    Watanabe, M., Nayar, S.: Rational filters for passive depth from defocus. Intl. J. of Comp. Vision 27, 203–225 (1998)CrossRefGoogle Scholar
  14. 14.
    Chaudhuri, S., Rajagopalan, A.: Depth from defocus: a real aperture imaging approach. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  15. 15.
    Born, M., Wolf, E.: Principle of optics. Pergamon Press, Oxford (1980)Google Scholar
  16. 16.
    Weickert, J.: Anisotropic Diffusion in Image Processing. B.G.Teubner Stuttgart (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Paolo Favaro
    • 1
  • Enrico Grisan
    • 2
  1. 1.Siemens Corporate ResearchPrincetonUSA
  2. 2.Department of Information EngineeringUniversitá di PadovaItaly

Personalised recommendations