Title :
A three-dimensional model of human lip motions trained from video
Author :
Basu, Sumit ; Pentland, Alex
Author_Institution :
Perceptual Comput. Sect., MIT, Cambridge, MA, USA
Abstract :
We present a 3D model of human lips and develop a framework for training it from real data. The model starts off with generic physics specified with the finite element method and “learns” the correct physics through observations. The model´s physics allow physically-based regularization between sparse observation points and the resulting set of deformations are used to derive the correct physical modes of the model. Preliminary results showing the model´s ability to reconstruct lip shapes from sparse data are shown. The resulting model can be used for both analysis and synthesis
Keywords :
computational geometry; computer animation; finite element analysis; image reconstruction; motion estimation; solid modelling; user interfaces; 3D model; deformations; finite element method; generic physics; human lip motions; learning; lip shape reconstruction; observations; physically-based regularization; sparse data; sparse observation points; three-dimensional model; training; video; Deformable models; Finite element methods; Head; Humans; Laboratories; Lips; Physics; Robustness; Shape; Tracking;
Conference_Titel :
Nonrigid and Articulated Motion Workshop, 1997. Proceedings., IEEE
Conference_Location :
San Juan
Print_ISBN :
0-8186-8040-7
DOI :
10.1109/NAMW.1997.609851
