There are five different approaches for facial animation:
interpolation, performance driven, muscle-based, pseudo
muscle-based and direct parameterization animation.
Interpolation is one of the most intuitive ways to animate a
3D face model. Given at least two key frames intermediate
frames can be produced by linear interpolation, bilinear
interpolation or nonlinear interpolation. This approach is also
known as key-frame animation [5]. In Performance driven
animation facial features are tracked through a sequence of
facial expression images and their movement is copied to a
new face to synthesize facial expression [6]. Physical muscle
modeling mathematically describes the properties and the
behavior of human skin, bone, and muscle systems. Pseudo
muscle models mimic the dynamics of human tissue with
heuristic geometric deformations [7].The most commonly
used animation approaches nowadays are direct
parameterization, where facial animation is parameterized by
a set of animation parameters [8]. These parameters not only
govern global animation of the head but also are able to
emulate a variety of facial expressions, overcoming the
limitation of expression interpolation. The typical parameters
are the affme transformation parameters, AUs and FAPs etc