Learning 3D Appearance Models from Video

Fernando De la Torre Frade, Jordi Casoliva-Rodon, and Jeffrey Cohn
Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004, pp. 645 - 651.


Download
  • Adobe portable document format (pdf) (574KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Within the past few years, there has been a great interest in face modeling for analysis (e.g. facial expression recognition) and synthesis (e.g. virtual avatars). Two primary approaches are appearance models (AM) and structure from motion (SFM). While extensively studied, both approaches have limitations. We introduce a semi-automatic method for 3D facial appearance modeling from video that addresses previous problems. Four main novelties are proposed:
  • A 3D generative facial appearance model integrates both structure and appearance.
  • The model is learned in a semi-unsupervised manner from video sequences, greatly reducing the need for tedious manual pre-processing.
  • A constrained flow-based stochastic sampling technique improves specificity in the learning process.
  • In the appearance learning step, we automatically select the most representative images from the sequence. By doing so, we avoid biasing the linear model, speed up processing and enable more tractable computations.
Preliminary experiments of learning 3D facial appearance models from video are reported.

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Number of pages: 7

Text Reference
Fernando De la Torre Frade, Jordi Casoliva-Rodon, and Jeffrey Cohn, "Learning 3D Appearance Models from Video," Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004, pp. 645 - 651.

BibTeX Reference
@inproceedings{De_la_Torre_Frade_2004_4807,
   author = "Fernando {De la Torre Frade} and Jordi Casoliva-Rodon and Jeffrey Cohn",
   title = "Learning 3D Appearance Models from Video",
   booktitle = "Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition",
   pages = "645 - 651",
   year = "2004",
}