Using 3-dimensional meshes to combine image-based and geometry-based constraints

  • P. Fua
  • Y. G. Leclerc
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


To recover complicated surfaces, single information sources often prove insufficient. In this paper, we present a unified framework for 3-D shape reconstruction that allows us to combine image-based constraints, such as those deriving from stereo and shape-from-shading, with geometry-based ones, provided here in the form of 3-D points, 3-D features or 2-D silhouettes.

Our approach to shape recovery is to deform a generic object-centered 3-D representation of the surface so as to minimize an objective function. This objective function is a weighted sum of the contributions of the various information sources. We describe these various terms individually, our weighting scheme and our optimization method. Finally, we present results on a number of difficult images of real scenes for which a single source of information would have proved insufficient.


Objective Function Geometric Constraint Surface Reconstruction Shape Recovery Laser Range Finder 
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. [Blake et al., 1985]
    A. Blake, A. Zisserman, and G. Knowles. Surface descriptions from stereo and shading. Image Vision Computation, 3(4):183–191, 1985.Google Scholar
  2. [Cryer et al., 1992]
    J. E. Cryer, Ping-Sing Tsai, and Mubarak Shah. Combining shape from shading and stereo using human vision model. Technical Report CS-TR-92-25, U. Central Florida, 1992.Google Scholar
  3. [Delingette et al., 1991]
    H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In Conference on Computer Vision and Pattern Recognition, pages 467–472, 1991.Google Scholar
  4. [Fua and Leclerc, 1993]
    P. Fua and Y.G. Leclerc. Object-centered surface reconstruction: Combining multi-image stereo and shading. In ARPA Image Understanding Workshop, Washington, D.C., April 1993.Google Scholar
  5. [Heipke, 1992]
    C. Heipke. Integration of digital image matching and multi image shape from shading. In International Society for Photogrammetry and Remote Sensing, pages 832–841, Washington D.C., 1992.Google Scholar
  6. [Kass et al., 1988]
    M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, 1(4):321–331, 1988.Google Scholar
  7. [Leclerc, 1989]
    Y.G. Leclerc. Constructing simple stable descriptions for image partitioning. International Journal of Computer Vision, 3(1):73–102, 1989.Google Scholar
  8. [Liedtke et al., 1991]
    C. E. Liedtke, H. Busch, and R. Koch. Shape adaptation for modelling of 3D objects in natural scenes. In Conference on Computer Vision and Pattern Recognition, pages 704–705, 1991.Google Scholar
  9. [Szeliski and Tonnesen, 1992]
    R. Szeliski and D. Tonnesen. Surface modeling with oriented particle systems. In Computer Graphics (SIGGRAPH'92), pages 185–194, July 1992.Google Scholar
  10. [Terzopoulos and Vasilescu, 1991]
    D. Terzopoulos and M. Vasilescu. Sampling and reconstruction with adaptive meshes. In Conference on Computer Vision and Pattern Recognition, pages 70–75, 1991.Google Scholar
  11. [Terzopoulos, 1986]
    D. Terzopoulos. Regularization of inverse visual problems involving discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:413–424, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • P. Fua
    • 1
  • Y. G. Leclerc
    • 1
  1. 1.SRI InternationalMenlo ParkUSA

Personalised recommendations