Multiscale Inverse Compositional Alignment for Subdivision Surface Maps

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


We propose an efficient alignment method for textured Doo-Sabin subdivision surface templates. A variation of the inverse compositional image alignment is derived by introducing smooth adjustments in the parametric space of the surface and relating them to the control point increments. The convergence properties of the proposed method are improved by a coarse-to-fine multiscale matching. The method is applied to real-time tracking of specially marked surfaces from a single camera view.


Template Match Subdivision Surface Surface Template Control Vertex Template Match Algorithm 
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. 1.
    Matthews, I., Baker, S.: Active appearance models revisited. Technical Report CMU-RI-TR-03-02, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA (2003)Google Scholar
  2. 2.
    Cascia, M.L., Sclaroff, S., Athitsos, V.: Fast, reliable head tracking under varying illumination: An approach based on robust registration of texture-mapped 3d models. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI) 22 (2000)Google Scholar
  3. 3.
    Zorin, D., Schröder, P. (eds.): Subdivision for Modeling and Animation. Course Notes. ACM SIGGRAPH (1999)Google Scholar
  4. 4.
    Baker, S., Matthews, I.: Equivalence and efficiency of image alignment algorithms. In: Proc. of the CVPR (2001)Google Scholar
  5. 5.
    Szeliski, R., Shum, H.Y.: Motion estimation with quadtree splines. IEEE Transactions on Pattern Analysis and Machine Intelligence 18, 1199–1210 (1996)CrossRefGoogle Scholar
  6. 6.
    Simoncelli, E.: Bayesian multi-scale differential optical flow. In: Handbook of Computer Vision and Applications, pp. 128–129 (1993)Google Scholar
  7. 7.
    Borgefors, G.: Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence 10, 849–865 (1988)CrossRefGoogle Scholar
  8. 8.
    Sclaroff, S., Isidoro, J.: Active blobs. In: Proceedings of ICCV 1998, pp. 1146–1153 (1998)Google Scholar
  9. 9.
    Doo, D., Sabin, M.: Behaviour of recursive division surfaces near extraordinary points. Computer-Aided Design 10, 356–360 (1978)CrossRefGoogle Scholar
  10. 10.
    Warren, J., Weimer, H.: Subdivision Methods For Geometric Design: A Constructive Approach. Morgan Kaufmann, San Francisco (2001)Google Scholar
  11. 11.
    Zorin, D., Schröder, P.: A unified framework for primal/dual quadrilateral subdivision schemes. CAGD 18, 429–454 (2001)zbMATHGoogle Scholar
  12. 12.
    Shi, J., Tomasi, C.: Good features to track. In: CVPR, pp. 593–600 (1994)Google Scholar
  13. 13.
    Guskov, I., Klibanov, S., Bryant, B.: Trackable surfaces. In: Proceedings of ACM/EG Symposium on Computer Animation, pp. 251–257 (2003)Google Scholar
  14. 14.
    Gleicher, M.: Projective registration with difference decomposition. In: Proc. of IEEE CVPR 1997, pp. 331–337 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  1. 1.University of MichiganAnn ArborUSA

Personalised recommendations