Intelligent Expression Blending for Performance Driven Facial Animation

Performance-Driven Facial Animation (PDFA) allows an animator to specify the desired facial action in terms of detected face movements of a performer. The animation system works by mimicking the actions of the performer on an animated character. Research efforts in PDFA have mostly concentrated on efficient tracking and re-targeting of facial expressions; very little attention has been paid to the intelligent enhancement of expressions. This paper describes an intelligent system that automatically enhances facial expressions in a PDFA sequence in light of its context. The system models facial expressions as MPEG-4 compliant fuzzy streams. The video context is processed by a fuzzy rule based system (FRBS) in order to find out what expression needs to be added to the detected expression to enhance its naturalness. The FRBS then intelligently blends the detected expression and the expression implied by the context to generate the enhanced expression parameters which are used to animate the target 3D facial model.