Synthesizing Realistic Facial Expressions From Photographs
Frédéric Pighin, Jamie Hecker, Dani Lischinski, Richard Szeliski, David H. Salesin
Proceedings of SIGGRAPH 98, July 1998, pp. 75--84.
Abstract: We present new techniques for creating photorealistic textured 3D facial models from photographs of a human subject, and for creating smooth transitions between different facial expressions by morphing between these different models. Starting from several uncalibrated views of a human subject, we employ a user-assisted technique to recover the camera poses corresponding to the views as well as the 3D coordinates of a sparse set of chosen locations on the subject's face. A scattered data interpolation technique is then used to deform a generic face mesh to fit the particular geometry of the subject's face. Having recovered the camera poses and the facial geometry, we extract from the input images one or more texture maps for the model. This process is repeated for several facial expressions of a particular subject. To generate transitions between these facial expressions we use 3D shape morphing between the corresponding face models, while at the same time blending the corresponding textures. Using our technique, we have been able to generate highly realistic face models and natural looking animations.
Keyword(s): facial modeling, facial expression generation, facial animation, photogrammetry, morphing, view-dependent texture-mapping
BibTeX format:
@inproceedings{Pighin:1998:SRF,
  author = {Frédéric Pighin and Jamie Hecker and Dani Lischinski and Richard Szeliski and David H. Salesin},
  title = {Synthesizing Realistic Facial Expressions From Photographs},
  booktitle = {Proceedings of SIGGRAPH 98},
  pages = {75--84},
  month = jul,
  year = {1998},
}
Search for more articles by Frédéric Pighin.
Search for more articles by Jamie Hecker.
Search for more articles by Dani Lischinski.
Search for more articles by Richard Szeliski.
Search for more articles by David H. Salesin.

Return to the search page.


graphbib: Powered by "bibsql" and "SQLite3."