An Evaluation of Three Popular Computer Vision Approaches for 3-D Face Synthesis

  • Alexander Woodward
  • Da An
  • Yizhe Lin
  • Patrice Delmas
  • Georgy Gimel’farb
  • John Morris
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4109)


We have evaluated three computer approaches to 3-D reconstruction – passive computational binocular stereo and active structured lighting and photometric stereo – in regard to human face reconstruction for modelling virtual humans. An integrated experimental environment simultaneously acquired images for 3-D reconstruction and data from a 3-D scanner which provided an accurate ground truth. Our goal was to determine whether today’s computer vision approaches are accurate and fast enough for practical 3-D facial reconstruction applications. We showed that the combination of structured lighting with symmetric dynamic programming stereo has good prospects with reasonable processing time and accuracy.


Gray Code Structure Lighting Dynamic Program Method Virtual Human Face Reconstruction 
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.
    Ayache, N., Hansen, C.: Rectification of Images for Binocular and Trinocular Stereovision. In: Proc. 9th Int. Conf. on Pattern Recognition, Rome. IEEE CS Press, Los Alamitos (1988)Google Scholar
  2. 2.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)CrossRefGoogle Scholar
  3. 3.
    Chan, M., Delmas, P., Gimel’farb, G., Leclercq, P.: Comparative study of 3d face acquisition techniques. In: Gagalowicz, A., Philips, W. (eds.) CAIP 2005. LNCS, vol. 3691, pp. 740–747. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    An, D., Woodward, A., Delmas, P., Chen, C.: Comparison of Structured Lighting Techniques with a View for Facial Reconstruction. In: Proc. Image and Vision Computing New Zealand Conf., Dunedin, New Zealand, pp. 195–200 (2005)Google Scholar
  5. 5.
    Klette, R., Schluns, K.: Computer Vision - Three-dimensional Data from Images. Springer, Berlin (1998)MATHGoogle Scholar
  6. 6.
    Kurihara, T., Arai, K.: A transformation method for modeling and animation of the human face from photographs. In: Proc. Computer Animation 1991 Conf., Tokyo, pp. 45–58 (1991)Google Scholar
  7. 7.
    Leclercq, P., Liu, J., Chan, M., Woodward, A., Gimel’farb, G., Delmas, P.: Comparative study of stereo algorithms for 3D face reconstruction. In: Proc. Int. Conf. on Advanced Concepts for Intelligent Vision Systems, Brussels, Belgium (September 2004)Google Scholar
  8. 8.
    Lee, Y., Terzopoulos, D., Waters, K.: Realistic modeling for facial animation. In: Proc. ACM SIGGRAPH 1995 Conf., pp. 55–62 (1995)Google Scholar
  9. 9.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision 47(1), 7–42 (2002)MATHCrossRefGoogle Scholar
  10. 10.
    Wen, Z., Huang, T.S.: 3D Face Processing: Modeling, Analysis and Synthesis. The International Series in Video Computing, vol. 8. Springer, Berlin (2004)Google Scholar
  11. 11.
    Woodward, A., Delmas, P.: Towards a low cost realistic human face modelling and animation framework. In: Proc. Image and Vision Computing New Zealand, Akaroa, Christchurch, New Zealand, pp. 11–16 (November 2004)Google Scholar
  12. 12.
    Woodward, A.M., Delmas, P.: Synthetic Ground Truth for Comparison of Gradient Field Integration Methods for Human Faces. In: Proc. Image and Vision Computing New Zealand, Dunedin, New Zealand, pp. 155–160 (November 2005)Google Scholar
  13. 13.
    Tsai, R.Y.: A Versatile Camera Calibration Technique for High Accuracy 3-D Machine Vision Metrology using Off the Shelf TV Cameras and Lenses. Int. J. Robotics and Automation 3(4), 323–344 (1987)CrossRefGoogle Scholar
  14. 14.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient Belief Propagation for Early Vision. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 261–268. IEEE CS Press, Los Alamitos (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alexander Woodward
    • 1
  • Da An
    • 1
  • Yizhe Lin
    • 1
  • Patrice Delmas
    • 1
  • Georgy Gimel’farb
    • 1
  • John Morris
    • 1
  1. 1.Dept. of Computer ScienceThe University of AucklandAucklandNew Zealand

Personalised recommendations