TR2003-81

Silhouette-Based 3D Face Shape Recovery


    •  Lee, J., Moghaddam, B., Pfister, H., Machiraju, R., "Silhouette-Based 3D Face Shape Recovery", Graphics Interface, June 2003.
      BibTeX TR2003-81 PDF
      • @inproceedings{Lee2003jul,
      • author = {Lee, J. and Moghaddam, B. and Pfister, H. and Machiraju, R.},
      • title = {Silhouette-Based 3D Face Shape Recovery},
      • booktitle = {Graphics Interface},
      • year = 2003,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2003-81}
      • }
  • Research Area:

    Computer Vision

Abstract:

The creation of realistic 3D face models is still a fundamental problem in computer graphics. In this paper we present a novel method to obtain the 3D shape of an arbitrary human face using a sequence of silhouette images as input. Our face model is a linear combination of eigenheads, which are obtained by a Principal Component Analysis (PCA) of laser-scanned 3D human faces. The coefficients of this linear decomposition are used as our model parameters. We introduce a near-automatic method for reconstructing a 3D face model whose silhouette images match closest to the set of input silhouettes.

 

  • Related News & Events