Accurate and efficient reconstruction of 3D faces from stereo images

Vuong Le, Hao Tang, Liangliang Cao, Thomas S. Huang

Abstract

In this paper, we propose a novel algorithm for reconstructing the 3D shape and texture of human faces from two stereo images, which are captured from calibrated cameras. Our approach works in a sparse to dense manner: we first build a coarse shape estimation based on 3D keypoints, and then use a linear morphable model to efficiently match the detail shape and texture. Compared with the previous works, our algorithm can reconstruct the 3D face shape in a speed comparable with that of the fastest algorithm available, but gives a higher accuracy. It can also recover the texture with more complete, realistic looking. Our results show that the new algorithm possesses significant characteristics of a 3D face model reconstruction system, and is especially useful for face recognition and animation applications in practice.
BibTeX
@inproceedings{le2010accurate,
  author = {Vuong Le and Hao Tang and Liangliang Cao and Thomas S. Huang},
  title = {{Accurate and efficient reconstruction of 3D faces from stereo images}},
  booktitle = {ICIP},
  year = {2010},
  doi = {10.1109/icip.2010.5651875},
}
Figure