We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a number of salient features on the human face as the output of a dynamical system made up of two subsystems, one driven by the deterministic speech input, and a second driven by an unknown stochastic input. Inference of the model (learning) is performed automatically and involves an extension of independent component analysis to time-depentend data. Using a shapetexture decompositional representation for the face, we generate facial image sequences reconstructed from synthesized feature point positions.

We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a number of salient features on the human face as the output of a dynamical system made up of two subsystems, one driven by the deterministic speech input, and a second driven by an unknown stochastic input. Inference of the model (learning) is performed automatically and involves an extension of independent component analysis to time-depentend data. Using a shape-texture decompositional representation for the face, we generate facial image sequences reconstructed from synthesized feature point positions.

We present a fast visual feature tracking system which takes advantage of dedicated hardware to perform the computationally intensive step of selection. A software system uses the output of the hardware selector to develop tracks using filtering and data association techniques, and image-based validation. By using separate, custom hardware to select hundreds of points per frame then associating these points to tracks in software, we achieve greater than 60Hz real-time tracking.