Layer Extraction with a Bayesian Model of Shapes

  • P. H. S. Torr
  • A. R. Dick
  • R. Cipolla
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1843)


This paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape. A probabilistic hierarchical model of layer shape is constructed, which assigns a density function to the shape and spatial relationships between layers. This allows accurate and efficient algorithms to be used when finding the best segmentation. Here this framework is applied to architectural scenes, in which layers commonly correspond to windows or doors and hence belong to a tightly constrained family of shapes.


Structure from motion Grouping and segmentation 


  1. 1.
    S. Ayer and H. Sawhney. Layered representation of motion video using robust maximum-likelihood estimation of mixture models and mdl encoding. In International Conference on Computer Vision, pages 777–784, 1995.Google Scholar
  2. 2.
    S. Baker, R. Szeliski, and P. Anandan. A layered approach to stereo reconstruction. In IEEE Computer Vision and Pattern Recognition, pages 434–441, 1998.Google Scholar
  3. 3.
    R. Cipolla, D. Robertson, and E. Boyer. Photobuilder-3d models of architectural scenes from uncalibrated images. In IEEE Int. Conf. on Multimedia Computing and Systems, 1999.Google Scholar
  4. 4.
    A.R. Dick and R. Cipolla. Model refinement from planar parallax. In Proc. 10th British Machine Vision Conference (BMVC’99), volume 1, pages 73–82, Nottingham, 1999.Google Scholar
  5. 5.
    A. Gelman, J. Carlin, H. Stern, and D. Rubin. Bayesian Data Analysis. Chapman and Hall, Boston, 1995.Google Scholar
  6. 6.
    U. Grenander, Y. Chow, and D.M. Keenan. HANDS. A Pattern Theoretical Study of Biological Shapes. Springer-Verlag. New York, 1991.Google Scholar
  7. 7.
    F. Heitz and P. Bouthemy. Multimodal motion estimation and segmentation using markov random fields. In Proc. 10th Int. Conf. Pattern Recognition, pages 378–383, 1991.Google Scholar
  8. 8.
    A. Jepson and M. Black. Mixture models for optical flow computation. In IEEE Computer Vision and Pattern Recognition, pages 760–766. IEEE, 1993.Google Scholar
  9. 9.
    R. Koch, M. Pollefeys, and L. Van Gool. Multi viewpoint stereo from uncalibrated video sequences. In European Conference on Computer Vision, pages 55–71, 1998.Google Scholar
  10. 10.
    D. J. C. MacKay. Bayesian interpolation. Neural Computation, 4(3):415–447, 1992.CrossRefGoogle Scholar
  11. 11.
    J. Magarey and N. Kingsbury. Motion estimation using a complex-valued wavelet transform. IEEE Trans. Signal Processing, 46(4):1069–1084, April 1998.Google Scholar
  12. 12.
    M. Pollefeys, R. Koch, and L. VanGool. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. In International Conference on Computer Vision, pages 90–95, 1998.Google Scholar
  13. 13.
    G. Schwarz. Estimating dimension of a model. Ann. Stat., 6:461–464, 1978.zbMATHCrossRefGoogle Scholar
  14. 14.
    S. Seitz and C. Dyer. A theory of shape by space carving. In International Conference on Computer Vision, pages 307–314, 1999.Google Scholar
  15. 15.
    H.Y. Shum, M. Han, and R. Szeliski. Interactive construction of 3d models from panoramic mosaics. In IEEE Computer Vision and Pattern Recognition, pages 427–433, 1998.Google Scholar
  16. 16.
    D. S. Sivia. Data Analysis: A Bayesian Tutorial. Oxford University Press, Oxford, 1996.zbMATHGoogle Scholar
  17. 17.
    P. Torr, R. Szeliski, and P. Anandan. An integrated bayesian approach to layer extraction from image sequences. In International Conference on Computer Vision, pages 983–990, 1999.Google Scholar
  18. 18.
    J. Wang and E. H. Adelson. Layered representation for motion analysis. In IEEE Computer Vision and Pattern Recognition, pages 361–366, 1993.Google Scholar
  19. 19.
    T. Weiss and E. H. Adelson. A unified mixture framework for motion segmentation. In IEEE Computer Vision and Pattern Recognition, pages 321–326, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • P. H. S. Torr
    • 1
  • A. R. Dick
    • 2
  • R. Cipolla
    • 2
  1. 1.Microsoft ResearchCambridgeUK
  2. 2.Department of EngineeringUniversity of CambridgeCambridgeUK

Personalised recommendations