Advertisement

A Probabilistic Theory of Occupancy and Emptiness

  • Rahul Bhotika
  • David J. Fleet
  • Kiriakos N. Kutulakos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)

Abstract

This paper studies the inference of 3D shape from a set of n noisy photos. We derive a probabilistic framework to specify what one can infer about 3D shape for arbitrarily-shaped, Lambertian scenes and arbitrary viewpoint configurations. Based on formal definitions of visibility, occupancy, emptiness, and photo-consistency, the theoretical development yields a formulation of the Photo Hull Distribution, the tightest probabilistic bound on the scene’s true shape that can be inferred from the photos. We show how to (1) express this distribution in terms of image measurements, (2) represent it compactly by assigning an occupancy probability to each point in space, and (3) design a stochastic reconstruction algorithm that draws fair samples (i.e., 3D photo hulls) from it. We also present experimental results for complex 3D scenes.

Keywords

Visibility State Probabilistic Dependency Occupancy Probability Fair Sample Input Photo 
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.

References

  1. 1.
    A. Elfes, “Sonar-based real-world mapping and navigation,” IEEE J. Robotics Automat., vol. 3, no. 3, pp. 249–266, 1987.Google Scholar
  2. 2.
    B. Curless and M. Levoy, “A volumetric method for building complex models from range images,” in Proc. SIGGRAPH’96, pp. 303–312, 1996.Google Scholar
  3. 3.
    D. Marr and T. Poggio, “A computational theory of human stereo vision,” Proceedings of the Royal Society of London B, vol. 207, pp. 187–217, 1979.CrossRefGoogle Scholar
  4. 4.
    L. Matthies, “Stereo vision for planetary rovers: Stochastic modeling to near real-time implementation,” Int. J. Computer Vision, vol. 8, no. 1, pp. 71–91, 1992.CrossRefMathSciNetGoogle Scholar
  5. 5.
    T. Kanade and M. Okutomi, “A stereo matching algorithm with an adaptive window: Theory and experiment,” IEEE Trans. PAMI, vol. 16, no. 9, pp. 920–932, 1994.Google Scholar
  6. 6.
    I. Cox, S. Hingorani, S. Rao, and B. Maggs, “A maximum likelihood stereo algorithm,” CVIU: Image Understanding, vol. 63, no. 3, pp. 542–567, 1996.CrossRefGoogle Scholar
  7. 7.
    H. Ishikawa and D. Geiger, “Occlusions, discontinuities and epipolar line in stereo,” in Proc. 5th European Conf. on Computer Vision, pp. 232–248, 1998.Google Scholar
  8. 8.
    P. N. Belhumeur, “A Bayesian approach to binocular stereopsis,” Int. J. on Computer Vision, vol. 19, no. 3, pp. 237–260, 1996.CrossRefGoogle Scholar
  9. 9.
    R. Szeliski, “Bayesian modeling of uncertainty in low-level vision,” Int. J. Computer Vision, vol. 5, no. 3, pp. 271–301, 1990.CrossRefGoogle Scholar
  10. 10.
    D. Geiger and F. Girosi, “Parallel and deterministic algorithms from MRF’s: surface reconstruction,” IEEE Trans. PAMI, vol. 13, no. 5, pp. 401–412, 1991.Google Scholar
  11. 11.
    K. Kanatani and N. Ohta, “Accuracy bounds and optimal computation of homography for image mosaicing applications,” in Proc. 7th Int. Conf. on Computer Vision, vol. 1, pp. 73–78, 1999.CrossRefGoogle Scholar
  12. 12.
    P. Torr, R. Szeliski, and P. Anandan, “An integrated bayesian approach to layer extraction from image sequences,” IEEE Trans. PAMI, vol. 23, no. 3, pp. 297–303, 2001.Google Scholar
  13. 13.
    P. Fua and Y. G. Leclerc, “Object-centered surface reconstruction: Combining multi-image stereo and shading,” Int. J. Computer Vision, vol. 16, pp. 35–56, 1995.CrossRefGoogle Scholar
  14. 14.
    R. T. Collins, “A space-sweep approach to true multi-image matching,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 358–363, 1996.Google Scholar
  15. 15.
    S. M. Seitz and C. R. Dyer, “Photorealistic scene reconstruction by voxel coloring,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 1067–1073, 1997.Google Scholar
  16. 16.
    S. Roy and I. J. Cox, “A maximum-flow formulation of the N-camera stereo correspondence problem,” in Proc. 6th Int. Conf. on Computer Vision, pp. 492–499, 1998.Google Scholar
  17. 17.
    O. Faugeras and R. Keriven, “Complete dense stereovision using level set methods,” in Proc. 5th European Conf. on Computer Vision, pp. 379–393, 1998.Google Scholar
  18. 18.
    K. N. Kutulakos, “Approximate N-View stereo,” in Proc. European Conf. on Computer Vision, pp. 67–83, 2000.Google Scholar
  19. 19.
    K. N. Kutulakos and S. M. Seitz, “A theory of shape by space carving,” Int. J. Computer Vision, vol. 38, no. 3, pp. 199–218, 2000. Marr Prize Special Issue.zbMATHCrossRefGoogle Scholar
  20. 20.
    J. D. Bonet and P. Viola, “Roxels: Responsibility-weighted 3D volume reconstruction,” in Prof. 7th. Int. Conf. on Computer Vision, pp. 418–425, 1999.Google Scholar
  21. 21.
    A. Broadhurst, T. Drummond, and R. Cipolla, “A probabilistic framework for space carving,” in Proc. 8th Int. Conf. on Computer Vision, pp. 388–393, 2001.Google Scholar
  22. 22.
    R. Bhotika, D. J. Fleet, and K. N. Kutulakos, “A probabilistic theory of occupancy and emptiness,” Tech. Rep. 753, University of Rochester Computer Science Department, Dec. 2001.Google Scholar
  23. 23.
    B. K. P. Horn, Robot Vision. MIT Press, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Rahul Bhotika
    • 1
  • David J. Fleet
    • 2
  • Kiriakos N. Kutulakos
    • 3
  1. 1.Computer Science DepartmentUniversity of RochesterRochesterUSA
  2. 2.Palo Alto Research CenterPalo AltoUSA
  3. 3.Computer Science DepartmentUniversity of TorontoTorontoCanada

Personalised recommendations