International Journal of Computer Vision

, Volume 1, Issue 3, pp 211–221 | Cite as

Symmetry-seeking models and 3D object reconstruction

  • Demetri Terzopoulos
  • Andrew Witkin
  • Michael Kass


We propose models of 3D shape which may be viewed as deformable bodies composed of simulated elastic material. In contrast to traditional, purely geometric models of shape, deformable models are active—their shapes change in response to externally applied forces. We develop a deformable model for 3D shape which has a preference for axial symmetry. Symmetry is represented even though the model does not belong to a parametric shape family such as (generalized) cylinders. Rather, a symmetry-seeking property is designed into internal forces that constrain the deformations of the model. We develop a framework for 3D object reconstruction based on symmetry-seeking models. Instances of these models are formed from monocular image data through the action of external forces derived from the data. The forces proposed in this paper deform the model in space so that the shape of its projection into the image plane is consistent with the 2D silhouette of an object of interest. The effectiveness of our approach is demonstrated using natural images.


Image Processing Computer Vision Image Data External Force Computer Image 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. Terzopoulos, “Multilevel computational processes for visual surface reconstruction,” Computer Vision, Graphics, and Image Processing, vol. 24, pp. 52–96, 1983.Google Scholar
  2. 2.
    T.O. Binford, “Visual perception by a computer,” Presented at the IEEE CONF. ON SYSTEMS AND CONTROL, Miami, Fla., 1971.Google Scholar
  3. 3.
    A. Barr, “Superquadrics and angle-preserving transformations,” IEEE Computer Graphics and Applications, vol. 18, pp. 21–30, 1981.Google Scholar
  4. 4.
    A.P. Pentland, “Parts: Structured descriptions of shape,” in PROC. NAT. CONF. ARTIF. INTEL., AAAI-86, Philadelphia, Pa., 1986, pp. 695–701.Google Scholar
  5. 5.
    J.M. Brady and H. Asada, “Smoothed local symmetries and their implementation,” Int. J. Robotics Res., vol. 3, pp. 33–61, 1984.Google Scholar
  6. 6.
    A. Witkin, M. Kass, D. Terzopoulos, and A. Barr, “Linking perception and graphics: Modeling with dynamic constraints,” in IMAGES AND UNDERSTANDING, H. Barlow, C. Blakemore, and W. Weston-Smith (eds.), Cambridge University Press, in press.Google Scholar
  7. 7.
    D. Terzopoulos, “Regularization of inverse visual problems involving discontinuities,” IEEE Trans. Pami, vol. 8, pp. 413–424, 1986.Google Scholar
  8. 8.
    G.A. Agin and T.O. Binford, “Computer description of curved objects,” in PROC. THIRD INT. JOINT CONF. ARTIF. INTELL., Stanford, Calif., 1973, pp. 629–635.Google Scholar
  9. 9.
    J.M. Hollerbach, Hierarchical shape description of objects by selection and modification of prototypes, M.I.T. Artif. Intel. Lab., Cambridge, Mass., AI-TR-346, 1975.Google Scholar
  10. 10.
    R. Nevatia and T.O. Binford, “Description and recognition of curved objects,” Artificial Intelligence, vol. 8, pp. 77–98, 1977.Google Scholar
  11. 11.
    D. Marr, “Analysis of occluding contour,” Proc. R. Soc. (London), B, vol. 197, pp. 441–475, 1977.Google Scholar
  12. 12.
    D. Marr and H.K. Nishihara, “Representation and recognition of the spatial organization of three-dimensional shapes,” Proc. R. Soc. (London), B, vol. 200, pp. 269–294, 1978.Google Scholar
  13. 13.
    R.A. Brooks, “Symbolic reasoning among 3-D models and 2-D images,” Artificial intelligence, vol. 17, pp. 285–348, 1981.Google Scholar
  14. 14.
    G.K. Rao and R. Nevatia, “Generalized cone descriptions from sparse 3-D data,” PROC. DARPA IMAGE UNDERSTANDING WORKSHOP, Miami Beach, Fla., L.S. Baumann (ed.), 1985, pp. 497–505.Google Scholar
  15. 15.
    H.A. Blum, “A transformation for extracting new descriptions of shape,” in PROC. SYMP. MODELS PERCEPT. SPEECH VISUAL FORM, Boston, Mass., 1964, pp. 362–380.Google Scholar
  16. 16.
    T. Kanade, “Recovery of the three dimensional shape of an object from a single view,” Artificial Intelligence, vol. 17, pp. 409–460, 1981.Google Scholar
  17. 17.
    J.M. Brady, “Criteria for representations of shape,” in Human and Machine Vision, A. Rosenfeld and J. Beck (eds.), Academic Press, New York, NY, 1983, pp. 39–84.Google Scholar
  18. 18.
    W.A. Richards and D.D. Hoffman, “Codon constraints on closed 2D shapes,” Computer Vision, Graphics, and Image Processing, vol. 31, pp. 265–281, 1985.Google Scholar
  19. 19.
    M. Leyton, “Constraint theorems on the prototypification of shape,” PROC. NAT. CONF. ARTIFI. INTEL., AAAI-86, Philadelphia, Pa., 1986, pp. 702–706.Google Scholar
  20. 20.
    M.A. Fischler and R.A. Elschlager, “The representation and matching of pictorial structures,” IEEE Trans. Computers, C-22, pp. 67–92, 1973.Google Scholar
  21. 21.
    A.H. Barr, “Global and local deformations of solid primitives,” Computer Graphics, vol. 18(3), pp. 21–29, 1984 (Proc. SIGGRAPH'84).Google Scholar
  22. 22.
    A.P. Pentland, “Recognition by parts,” PROC. FIRST INT. CONF. COMPUTER VISION, London, UK, 1987. pp. 612–620.Google Scholar
  23. 23.
    Y.C. Fung, Foundations of solid mechanics. Prentice-Hall: Englewood Cliffs, NJ, 1965.Google Scholar
  24. 24.
    G. Dahlquist and A. Björck, Numerical Methods, N. Anderson (trans.), Prentice-Hall: Englewood Cliffs, NJ, 1974.Google Scholar
  25. 25.
    A. Witkin, D. Terzopoulos and M. Kass, “Signal matching through scale space,” Int. J. of Computer vision, vol. 1(2), pp. 133–144, 1987.Google Scholar
  26. 26.
    D. Terzopoulos, “On matching deformable models to images: Direct and iterative solutions,” Topical Meeting on Machine Vision, Technical Digest Series, vol. 12. Optical Society of America: Washington, D.C., March, 1987, 160–167.Google Scholar
  27. 27.
    D. Terzopoulos, A. Witkin, and M. Kass, “Energy constraints on deformable models: recovering shape and non-rigid motion,” PROC. SIXTH NAT. CONF. ARTIFI. INTEL., AAAI-87, Seattle, Wash., July, 1987, pp. 755–760.Google Scholar
  28. 28.
    D. Rosenberg, M.D. Levine, and S.W. Zucker, “Computing relative depth from occlusion cues,” PROC. FOURTH INT. J. CONF. PATTERN RECOGNITION, Tokyo, 1978.Google Scholar
  29. 29.
    D. Terzopoulos, “Integrating visual information from multiple sources,” in From Pixels to Predicates: Recent Advances in Computational and Robotic Vision, A.P. Pentland (ed.). Ablex: Norwood, NJ, 1986, pp. 111–142.Google Scholar
  30. 30.
    D.G. Lowe, Perceptual Organization and Visual Recognition, Kluwer: Boston, Mass., 1985.Google Scholar
  31. 31.
    D. Terzopoulos, J. Platt, A. Barr, and K. Fleischer, “Elastically, deformable models,” Computer Graphics, 3 vol. 21, 1987, (Proc. SIGGRAPH'87), pp. 205–214.Google Scholar

Copyright information

© Kluwer Academic Publishers 1987

Authors and Affiliations

  • Demetri Terzopoulos
    • 1
  • Andrew Witkin
    • 1
  • Michael Kass
    • 1
  1. 1.Schlumberger Palo Alto ResearchPalo Alto

Personalised recommendations