Beauty with Variational Methods: An Optic Flow Approach to Hairstyle Simulation

  • Oliver Demetz
  • Joachim Weickert
  • Andrés Bruhn
  • Martin Welk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4485)


Although variational models offer many advantages in image analysis, their successful application to real-world problems is documented only for some specific areas such as medical imaging. In this paper we show how well-adapted variational ideas can solve the problem of hairstyle simulation in a fully automatic way: A customer in a hairdresser’s shop selects a new hairstyle from a database, and this hairstyle is automatically registered to a digital image of the customer’s face. Interestingly already a carefully modified optic flow method of Horn and Schunck turns out to be ideal for this application. These modifications include an extension to colour sequences, an incorporation of warping ideas in order to allow large deformation rates, and the inclusion of shape information that is characteristic for human faces. Employing classical numerical ideas such as finite differences and SOR iterations offers sufficient performance for real-life applications. In a number of experiments we demonstrate that our variational approach is capable of solving the hairstyle simulation problem with high quality in a fully practical setting.


Deformation Increment Large Linear System Medical Image Registration Previous Scale Reference Face 
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.
    Alvarez, L., et al.: Dense disparity map estimation respecting image derivatives: a PDE and scale-space based approach. Journal of Visual Communication and Image Representation 13(1-2), 3–21 (2002)CrossRefGoogle Scholar
  2. 2.
    Bajcsy, R., Kovacic, S.: Multiresolution elastic matching. Computer Vision, Graphics and Image Processing 46(1), 1–21 (1989)CrossRefGoogle Scholar
  3. 3.
    Bergen, J.R., et al.: Hierarchical model-based motion estimation. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 237–252. Springer, Heidelberg (1992)Google Scholar
  4. 4.
    Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(8), 775–790 (1991)CrossRefGoogle Scholar
  5. 5.
    Brox, T., et al.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Bruhn, A., et al.: Variational optic flow computation in real-time. IEEE Transactions on Image Processing 14(5), 608–615 (2005)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Chefd’Hotel, C., Hermosillo, G., Faugeras, O.: A variational approach to multi-modal image matching. In: Proc. First IEEE Workshop on Variational and Level Set Methods in Computer Vision, Vancouver, Canada, July 2001, pp. 21–28. IEEE Computer Society Press, Los Alamitos (2001)CrossRefGoogle Scholar
  8. 8.
    Cohen, I.: Nonlinear variational method for optical flow computation. In: Proc. Eighth Scandinavian Conference on Image Analysis, vol. 1, Tromsø, Norway, May 1993, pp. 523–530 (1993)Google Scholar
  9. 9.
    Golland, P., Bruckstein, A.M.: Motion from color. Computer Vision and Image Understanding 68(3), 346–362 (1997)CrossRefGoogle Scholar
  10. 10.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  11. 11.
    Lefébure, M., Cohen, L.D.: Image registration, optical flow and local rigidity. Journal of Mathematical Imaging and Vision 14(2), 131–147 (2001)CrossRefMathSciNetzbMATHGoogle Scholar
  12. 12.
    Mansouri, A.-R., Mitiche, A., Konrad, J.: Selective image diffusion: application to disparity estimation. In: Proc. 1998 IEEE International Conference on Image Processing, vol. 3, Chicago, IL, October 1998, pp. 284–288 (1998)Google Scholar
  13. 13.
    March, R.: Computation of stereo disparity using regularization. Pattern Recognition Letters 8, 181–187 (1988)CrossRefGoogle Scholar
  14. 14.
    Mémin, E., Pérez, P.: A multigrid approach for hierarchical motion estimation. In: Proc. Sixth International Conference on Computer Vision, Bombay, India, January 1998, pp. 933–938. Narosa Publishing House, New Delhi (1998)Google Scholar
  15. 15.
    Modersitzki, J.: Numerical Methods for Image Registration. Oxford University Press, Oxford (2004)zbMATHGoogle Scholar
  16. 16.
    Morton, K.W., Mayers, L.M.: Numerical Solution of Partial Differential Equations. Cambridge University Press, Cambridge (1994)zbMATHGoogle Scholar
  17. 17.
    Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 565–593 (1986)CrossRefGoogle Scholar
  18. 18.
    Papenberg, N., et al.: Highly accurate optic flow computation with theoretically justified warping. International Journal of Computer Vision 67(2), 141–158 (2006)CrossRefGoogle Scholar
  19. 19.
    Scherzer, O. (ed.): Mathematical Models for Registration and Applications to Medical Imaging. Springer, Berlin (2006)zbMATHGoogle Scholar
  20. 20.
    Young, D.M.: Iterative Solution of Large Linear Systems. Dover, New York (2003)zbMATHGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Oliver Demetz
    • 1
  • Joachim Weickert
    • 1
  • Andrés Bruhn
    • 1
  • Martin Welk
    • 1
  1. 1.Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Building E1.1, Saarland University, 66041 SaarbrückenGermany

Personalised recommendations