Skip to main content

Shape from appearance: A statistical approach to surface shape estimation

Part of the Lecture Notes in Computer Science book series (LNCS,volume 1064)

Abstract

This paper is concerned with surface shape estimation by a method in which an empirically determined associative model relating appearance to surface shape is used. Significantly, the estimated model is more accurate than the algorithm that generates the examples. The method presented here is a generalization of shape from shading methods that does not rely upon idealized models of the image formation process. As a relative of shape from shading, this method more accurately recovers small surface detail than is possible with methods such as stereo and motion. The present approach is a continuous analogue of pattern recognition and is closely related to methods of joint space learning used in robotics. Experiments on real scenes are used to illustrate the concepts involved.

Keywords

  • Surface Shape
  • Conditional Density
  • Level Curf
  • Real Scene
  • Associative Model

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.

This research was supported by the Advanced Research Projects Agency and the National Science Foundation under grant IRI-89-02728 and by the Army Advance Construction Technology Center under grant DAAL 03-87-K-0006.

References

  1. R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis. New York: John Wiley & Sons, 1973.

    Google Scholar 

  2. D. Forsyth and A. Zisserman, “Shape from shading in the light of mutual illumination,” Image Vision Comput., vol. 8, no. 1, pp 42–49, 1990.

    Google Scholar 

  3. D. R. Hougen and N. Ahuja, “Estimation of the Light Source Distribution and its Use in Shape Recovery from Stereo and Shading,” in Fourth Intl Conf. Comput. Vis., pp. 148–155, May 1993.

    Google Scholar 

  4. D. R. Hougen and N. Ahuja, “Adaptive Polynomial Modelling of the Reflectance for Shape Estimation from Stereo and Shading,” in Proc. IEEE Conf. Comput. Vis. Patt. Recog., pp. 991–994, June 1994.

    Google Scholar 

  5. D. R. Hougen and N. Ahuja, “Resolution and Accuracy of Stereo, Motion, and Shading Methods,” submitted to Comput. Vis. Patt. Recog., 1996.

    Google Scholar 

  6. Y. G. Leclerc and A. F. Bobick, “The direct computation of height from shading,” Proc. Comput. Vis. Patt. Recog., pp. 552–558, June 1991.

    Google Scholar 

  7. S. R. Lehky and T. J. Sejnowski, “Neural network model of visual cortex for determining surface curvature from images of shaded surfaces,” Proc. R. Soc. Lond. B, vol. 240, pp. 251–278, 1990.

    Google Scholar 

  8. S. Omohundro, “Geometric learning algorithms,” Physica D, vol. 42 pp. 307–321, 1990, and in Emergent Computation, ed. Stephanie Forrest, MIT Press 1991.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Hougen, D.R., Ahuja, N. (1996). Shape from appearance: A statistical approach to surface shape estimation. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015529

Download citation

  • DOI: https://doi.org/10.1007/BFb0015529

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61122-6

  • Online ISBN: 978-3-540-49949-7

  • eBook Packages: Springer Book Archive