Advertisement

Shading flows and scenel bundles: A new approach to shape from shading

  • Pierre Breton
  • Lee A. Iverson
  • Michael S. Langer
  • Steven W. Zucker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)

Abstract

The classical approach to shape from shading problems is to find a numerical solution of the image irradiance partial differential equation. It is always assumed that the parameters of this equation (the light source direction and surface albedo) can be estimated in advance. For images which contain shadows and occluding contours, this decoupling of problems is artificial. We develop a new approach to solving these equations. It is based on modern differential geometry, and solves for light source, surface shape, and material changes concurrently. Local scene elements (scenels) are estimated from the shading flow field, and smoothness, material, and light source compatibility conditions resolve them into consistent scene descriptions. Shadows and related difficulties for the classical approach are discussed.

Keywords

Surface Patch Cast Shadow Reflectance Function Shadow Boundary Light Source Direction 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ratliff, F.: Mach Bands: Quantitative Studies on Neural Networks in the Retina, Holden-Day, San Francisco (1965)Google Scholar
  2. 2.
    Horn, B.K.P.: “Obtaining Shape from Shading Information,” P.H. Winston. Ed. in The Psychology of Computer Vision, McGraw-Hill, New York (1975)Google Scholar
  3. 3.
    Ikeuchi, K. and Horn, B.K.P.: “Numerical Shape from Shading and Occluding Boundaries,” Artificial Intelligence, 17 (1981) 141–184CrossRefGoogle Scholar
  4. 4.
    Horn, B.K.P. and Brooks, M.J.: “The Variational Approach to Shape from Shading,” Comput. Vision, Graph. Image Process., 33 (1986) 174–208Google Scholar
  5. 5.
    Nayar, S.K., Ikeuchi, K. and Kanade, T.: “Shape From Interreflections,” International Journal of Computer Vision, 6 (1991) 173–195Google Scholar
  6. 6.
    Pentland, A.: “Linear Shape From Shading,” International Journal of Computer Vision, 4 (1990) 153–162Google Scholar
  7. 7.
    Husemoller, D.: Fibre Bundles, Springer, New York (1966)Google Scholar
  8. 8.
    Sander, P., and Zucker, S.W.: “Inferring Surface Trace and Differential Structure from 3-D Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, 9 (1990) 833–854Google Scholar
  9. 9.
    Spivak, M.: A Comprehensive Introduction to Differential Geometry, Publish or Perish, Berkeley (1979)Google Scholar
  10. 10.
    Pentland, A.: “Finding the Illuminant Direction,” J. Opt. Soc. Amer, 72 (1982) 448–455Google Scholar
  11. 11.
    K∄nderink, J.J.: “What Does the Occluding Contour Tell us about Solid Shape?,” Perception, 13 (1984) 321–330PubMedGoogle Scholar
  12. 12.
    K∄nderink, J.J. and van Dorn, A.J.: “The Shape of Smooth Objects and the Way Contours End,” Perception, 11 (1982) 129–137PubMedGoogle Scholar
  13. 13.
    Biederman, I.: “Recognition-by-Components: A Theory of Human Image Understanding,” Psychological Review, 94 (1987) 115–147PubMedGoogle Scholar
  14. 14.
    K∄nderink, J.J. and van Dorn, A.J.: “Photometric Invariants Related to Solid Shape,” Optica Acta, 27 (1980) 981–996Google Scholar
  15. 15.
    Iverson, L. and Zucker, S.W.: “Logical/Linear Operators for Measuring Orientation and Curvature,” TR-CIM-90-06, McGill University, Montreal, Canada (1990)Google Scholar
  16. 16.
    Zucker, S.W., Dobbins, A., and Iverson, L.: “Two Stages of Curve Detection Suggest Two Styles of Visual Computation,” Neural Computation, 1 (1989) 68–81Google Scholar
  17. 17.
    Hummel, A.R. and Zucker, S.W.: “On the Foundations of Relaxation Labeling Processes,” IEEE Trans. Pattern Anal. Machine Intell., 5 (1983) 267–287Google Scholar
  18. 18.
    Oliensis, J.: “Shape from Shading as a Partially Well-Constrained Problem,” Comp. Vis. Graph. Im. Proc., 54 (1991) 163–183Google Scholar
  19. 19.
    Hopfield, J.J.: “Neurons with Graded Response Have Collective Computational Properties like Those of Two-State Neurons,” Proc. Natl. Acad. Sci. USA, 81 (1984) 3088–3092PubMedGoogle Scholar
  20. 20.
    Miller, D.A. and Zucker, S.W.: “Efficient Simplex-like Methods for Equilibria of Nonsymmetric Analog Networks,” TR-CIM-91-3 McGill University, Montreal, Canada (1991); Neural Computation, (in press)Google Scholar
  21. 21.
    K∄nderink, J.J.: Solid Shape, MIT Press, Cambridge, Mass. (1990) p. 320Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Pierre Breton
    • 1
  • Lee A. Iverson
    • 1
  • Michael S. Langer
    • 1
  • Steven W. Zucker
    • 1
    • 2
  1. 1.Research Center for Intelligent MachineMcGill UniversityMontréalCanada
  2. 2.Canadian Institute for Advanced ResearchCanada

Personalised recommendations