Approximate N-View Stereo

  • Kiriakos N. Kutulakos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)


This paper introduces a new multi-view reconstruction problem called approximate N-view stereo. The goal of this problem is to recover a one-parameter family of volumes that are increasingly tighter supersets of an unknown, arbitrarily-shaped 3D scene. By studying 3D shapes that reproduce the input photographs up to a special image transformation called a shuffle transformation, we prove that (1) these shapes can be organized hierarchically into nested supersets of the scene, and (2) they can be computed using a simple algorithm called Approximate Space Carving that is provably-correct for arbitrary discrete scenes (i.e., for unknown, arbitrarily-shaped Lambertian scenes that are defined by a finite set of voxels and are viewed from N arbitrarily-distributed viewpoints inside or around them). The approach is specifically designed to attack practical reconstruction problems, including (1) recovering shape from images with inaccurate calibration information, and (2) building coarse scene models from multiple views.


Calibration Error Discrete Image Scene Point View Stereo Approximate Shape 
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.
    P. J. Narayanan, P. W. Rander, and T. Kanade, “Constructing virtual worlds using dense stereo,” in Proc. Int. Conf. on Computer Vision, pp. 3–10, 1998.Google Scholar
  2. 2.
    S. B. Kang and R. Szeliski, “3-D scene data recovery using omnidirectional multibaseline stereo,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 364–370, 1996.Google Scholar
  3. 3.
    R. Szeliski and P. Golland, “Stereo matching with transparency and matting,” in Proc. 6th Int. Conf. on Computer Vision, pp. 517–524, 1998.Google Scholar
  4. 4.
    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
  5. 5.
    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
  6. 6.
    K. N. Kutulakos and S. M. Seitz, “A theory of shape by space carving,” in Proc. 7th Int. Conf. Computer Vision, pp. 307–314, 1999.Google Scholar
  7. 7.
    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
  8. 8.
    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
  9. 9.
    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
  10. 10.
    G. Baratoff and Y. Aloimonos, “Changes in surface convexity and topology caused by distortions of stereoscopic visual space,” in Proc. 5th European Conf. on Computer Vision, pp. 226–240, 1998.Google Scholar
  11. 11.
    P. Fua and Y. G. Leclerc, “Registration without correspondences,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 121–128, 1994.Google Scholar
  12. 12.
    A. C. Prock and C. R. Dyer, “Towards real-time voxel coloring,” in Proc. Image Understanding Workshop, pp. 315–321, 1998.Google Scholar
  13. 13.
    R. Szeliski, “Rapid octree construction from image sequences,” CVGIP: Image Understanding, vol. 58, no. 1, pp. 23–32, 1993.CrossRefGoogle Scholar
  14. 14.
    T. Lindeberg, Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, 1994.Google Scholar
  15. 15.
    J. Popovic and H. Hoppe, “Progressive simplicial complexes,” in Proc. SIGGRAPH’97, pp. 189–198, 1997.Google Scholar
  16. 16.
    E. J. Stollnitz, T. D. DeRose, and D. H. Salesin, Wavelets for Computer Graphics. Morgan Kaufmann Publishers, 1996.Google Scholar
  17. 17.
    H. Samet, The design and analysis of spatial data structures. Reading, MA: Addison-Wesley, 1990.Google Scholar
  18. 18.
    J. J. Koenderink, Solid Shape.MIT Press, 1990.Google Scholar
  19. 19.
    P. Fua, “From multiple stereo views to multiple 3-d surfaces,” Int. J. Computer Vision, vol. 24, no. 1, pp. 19–35, 1997.CrossRefGoogle Scholar
  20. 20.
    R. Szeliski and H.-Y Shum, “Motion estimation with quadtree splines,” IEEE Trans. Pattern Anal. Machine Intell., vol. 18, no. 12, pp. 1199–1210, 1996.CrossRefGoogle Scholar
  21. 21.
    M. A. Armstrong, Basic Topology. Springer-Verlag, 1983.Google Scholar
  22. 22.
    J.L. Mundy and A. Zisserman, eds., Geometric Invariance in Computer Vision. MIT Press, 1992.Google Scholar
  23. 23.
    D. N. Bhat and S. K. Nayar, “Ordinal measures for visual correspondence,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 351–357, 1996.Google Scholar
  24. 24.
    J. Huang, S. R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih, “Image indexing using color correlograms,” in Proc. Computer Vision and Pattern Recognition Conf., pp. 762–768, 1997.Google Scholar
  25. 25.
    R. Zabih and J. Woodfill, “Non-parametric local transforms for computing visual correspondence,” in Proc. 3rd European Conf. on Computer Vision, pp. 151–158, 1994.Google Scholar
  26. 26.
    P. Meer, D. Mintz, A. Rosenfeld, and D. Y Kin, “Robust regression methods for computer vision: A review,” Int. J. Computer Vision, vol. 6, no. 1, pp. 59–70, 1991.CrossRefGoogle Scholar
  27. 27.
    S. J. Maybank and O. D. Faugeras, “A theory of self-calibration of a moving camera,” Int. J. Computer Vision, vol. 8, pp. 123–152, 1992.CrossRefGoogle Scholar
  28. 28.
    S. Birchfield and C. Tomasi, “A pixel dissimilarity measure that is insensitive to image sampling,” IEEE Trans. Pattern Anal. Machine Intell., vol. 20, no. 4, pp. 401–106, 1998.CrossRefGoogle Scholar
  29. 29.
    H. Cramér, Mathematical Methods of Statistics. Princeton University Press, 1946.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Kiriakos N. Kutulakos
    • 1
  1. 1.Department of Computer Science & Department of DermatologyUniversity of RochesterRochesterUSA

Personalised recommendations