Abstract
This paper compares the efficiency of several stereo matching algorithms in reconstructing 3D faces from both real and synthetic stereo pairs. The stereo image acquisition system setup and the creation of a face disparity map benchmark image are detailed. Ground truth is build by visual matching of corresponding nodes of a dense colour grid projected onto the faces. This experiment was also performed on a human face model created using OpenGL with mapped texture to create as perfect as possible a set for evaluation, instead of real human faces like our previous experiments. Performance of the algorithms is measured by deviations of the reconstructed surfaces from a ground truth prototype. This experiment shows that contrary to expectations, there is seemingly very little difference between the currently most known stereo algorithms in the case of the human face reconstruction. It is shown that by combining the most efficient but slow graph-cut algorithm with fast dynamic programming, more accurate reconstruction results can be obtained.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Wang, Q., Zhang, H., Riegeland, T., Hundt, E., Xu, G., Zhu, Z.: Creating animatable MPEG4 face. In: International Conference on Augmented Virtual Environments and Three Dimensional Imaging, Mykonos, Greece (2001)
Petajan, E.D., Bischoff, B., Bodoff, D., Brooke, N.M.: An improved automatic lipreading system to enhance speech recognition. In: CHI 1988, pp. 19–25 (1988)
Xiao, J., Baker, S., Matthews, I., Kanade, T.: Real–time combined 2D+3D active appearance models. IEEE International Conference on Computer Vision and Pattern Recognition (June 2004)
Faugeras, O., Hotz, B., Mathieu, H., Viéville, T., Zhang, Z., Fua, P., Théron, E., Moll, L., Berry, G., Vuillemin, J., Bertin, P., Proy, C.: Real time correlation-based stereo: algorithm, implementatinos and applications. Technical Report 2013, Institut National De Recherche en Informatique et en Automatique (INRIA), 06902 Sophia Antipolis, France (1993)
Leclercq, P., Morris, J.: Robustness to noise of stereo matching. In: IEEE Computer Society (ed.) Proceedings of the International Conference on Image Analysis and Processing (ICIAP 2003), Mantova, Italy, September 2003, pp. 606–611 (2003)
Zabih, R., Woodfill, J.: Non-parametric local transforms for computing visual correspondence. LNCS, vol. 800, pp. 151–158. Springer, Heidelberg (1994)
Chen, Q., Medioni, G.: Building 3-D human face models from two photographs. Journal of VSLI Signal Processing, 127–140 (2001)
Barnard, S.T., Fischler, M.A.: Computational stereo. Surveys 14, 553–572 (1982)
Gimel’farb, G.: Binocular stereo by maximizing the likelihood ratio relative to a random terrain. In: Klette, R., Peleg, S., Sommer, G. (eds.) RobVis 2001. LNCS, vol. 1998, pp. 201–208. Springer, Heidelberg (2001)
Roy, S., Cox, I.J.: A maximum-flow formulation of the n-camera stereo correspondence problem. In: IEEE Proceedings of International Conference on Computer Vision (ICCV1998), Bombay (1998)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: Proc. 7th Int. Conf. Computer Vision (ICCV 1999), Kerkyra, Corfu, Greece, September 20–25, pp. 377–384. IEEE Computer Society Press, Los Alamitos (1999)
Boykov, Y., Veksler, O., Zabih, R.: Markov random fields with efficient approximations. In: Computer Vision and Pattern Recognition Conference (CVPR 1998) (June 1998)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions via graph cuts. In: International Conference on Computer Vision (ICCV 2001) (July 2001)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)
Chan, M., Chen, C.F., Barton, G., Delmas, P., Gimel’farb, G., Leclercq, P., Fisher, T.: A strategy for 3D face analysis and synthesis. Image and Vision Computing New Zealand, 384–389 (2003)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47, 7–42 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leclercq, P., Liu, J., Woodward, A., Delmas, P. (2004). Which Stereo Matching Algorithm for Accurate 3D Face Creation ?. In: Klette, R., Žunić, J. (eds) Combinatorial Image Analysis. IWCIA 2004. Lecture Notes in Computer Science, vol 3322. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30503-3_53
Download citation
DOI: https://doi.org/10.1007/978-3-540-30503-3_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23942-0
Online ISBN: 978-3-540-30503-3
eBook Packages: Computer ScienceComputer Science (R0)