Exaggeration of facial expressions from facial motion capture data

We propose a method for exaggerating facial expressions derived from exaggeration mappings that transform facial motions into exaggerated motions.The exaggeration mapping of facial motions is defined by non-negative matrix factorization.Three-dimensional facial expressions are simulated using the exaggerating rate as an input value to convey the degree of variation.Experiments show the validity of the exaggeration mapping and facial expression simulations.