On the Recovery of Depth from a Single Defocused Image

  • Shaojie Zhuo
  • Terence Sim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)


In this paper we address the challenging problem of recovering the depth of a scene from a single image using defocus cue. To achieve this, we first present a novel approach to estimate the amount of spatially varying defocus blur at edge locations. We re-blur the input image and show that the gradient magnitude ratio between the input and re-blurred images depends only on the amount of defocus blur. Thus, the blur amount can be obtained from the ratio. A layered depth map is then extracted by propagating the blur amount at edge locations to the entire image. Experimental results on synthetic and real images demonstrate the effectiveness of our method in providing a reliable estimate of the depth of a scene.


Image processing depth recovery defocus blur Gaussian gradient markov random field 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barnard, S., Fischler, M.: Computational stereo. ACM Comput. Surv. 14(4), 553–572 (1982)CrossRefGoogle Scholar
  2. 2.
    Dhond, U., Aggarwal, J.: Structure from stereo: A review. IEEE Trans. Syst. Man Cybern. 19(6), 1489–1510 (1989)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Dellaert, F., Seitz, S.M., Thorpe, C.E., Thrun, S.: Structure from motion without correspondence. In: Proc. CVPR, pp. 557–564 (2000)Google Scholar
  4. 4.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. Int. J. Comput. Vision 9, 137–154 (1992)CrossRefGoogle Scholar
  5. 5.
    Asada, N., Fujiwara, H., Matsuyama, T.: Edge and depth from focus. Int. J. Comput. Vision 26(2), 153–163 (1998)CrossRefGoogle Scholar
  6. 6.
    Nayar, S., Nakagawa, Y.: Shape from focus. IEEE Trans. Pattern Anal. Mach. Intell. 16(8), 824–831 (1994)CrossRefGoogle Scholar
  7. 7.
    Favaro, P., Favaro, P., Soatto, S.: A geometric approach to shape from defocus. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 406–417 (2005)CrossRefGoogle Scholar
  8. 8.
    Pentland, A.P.: A new sense for depth of field. IEEE Trans. Pattern Anal. Mach. Intell. 9(4), 523–531 (1987)CrossRefGoogle Scholar
  9. 9.
    Moreno-Noguer, F., Belhumeur, P.N., Nayar, S.K.: Active refocusing of images and videos. ACM Trans. Graphics, 67 (2007)Google Scholar
  10. 10.
    Nayar, S.K., Watanabe, M., Noguchi, M.: Real-time focus range sensor. IEEE Trans. Pattern Anal. Mach. Intell. 18(12), 1186–1198 (1996)CrossRefGoogle Scholar
  11. 11.
    Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. ACM Trans. Graphics (2007)Google Scholar
  12. 12.
    Saxena, A., Sun, M., Ng, A.: Make3d: Learning 3d scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell., 1–1 (2008)Google Scholar
  13. 13.
    Namboodiri, V.P., Chaudhuri, S.: Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera. In: Proc. CVPR (2008)Google Scholar
  14. 14.
    Hecht, E.: Optics, 4th edn. Addison-Wesley, Reading (2001)Google Scholar
  15. 15.
    Komodakis, N., Tziritas, G., Paragios, N.: Performance vs computational efficiency for optimizing single and dynamic mrfs: Setting the state of the art with primal-dual strategies. Proc. CVIU 112(1), 14–29 (2008)Google Scholar
  16. 16.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Shaojie Zhuo
    • 1
  • Terence Sim
    • 1
  1. 1.School of ComputingNational University of SingaporeSingapore

Personalised recommendations