Automatic 3D Face Reconstruction from Single Images or Video
PDF
This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression-and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high-resolution 3D surface model.
| Author(s): | Breuer, P. and Kim, KI. and Kienzle, W. and Blanz, V. and Schölkopf, B. |
| Links: | |
| Number (issue): | 160 |
| Year: | 2007 |
| Month: | February |
| Day: | 0 |
| BibTeX Type: | Technical Report (techreport) |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Institution: | Max Planck Institute for Biological Cybernetics, Tübingen, Germany |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@techreport{4380,
title = {Automatic 3D Face Reconstruction from Single Images or Video},
abstract = {This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression-and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a
combination of linear projections. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high-resolution 3D surface model.},
number = {160},
organization = {Max-Planck-Gesellschaft},
institution = {Max Planck Institute for Biological Cybernetics, Tübingen, Germany},
school = {Biologische Kybernetik},
month = feb,
year = {2007},
author = {Breuer, P. and Kim, KI. and Kienzle, W. and Blanz, V. and Sch{\"o}lkopf, B.},
month_numeric = {2}
}