A new efficient expression generation and automatic cloning method for multimedia actors

This paper describes a new and efficient method for facial expression gener ation on cloned synthetic head models. The system uses abstract facial musc les called action units (AUs) based on both anatomical muscles and the faci al action coding system. The facial expression generation method has real-t ime performance, is less computationally expensive than physically based mo dels, and has greater anatomical correspondence than rational free-form def ormation or spline-based techniques. Automatic cloning of a real human head is done by adapting a generic facial and head mesh to Cyberware laser scan ned data. The conformation of the generic head to the individual data and t he fitting of texture onto it are based on a fully automatic feature extrac tion procedure. Individual facial animation parameters are also automatical ly estimated during the conformation process. The entire animation system i s hierarchical; emotions and visemes (the visual mouth shapes that occur du ring speech) are defined in terms of the AUs, and higher-level gestures are defined in terms of AUs, emotions, and visemes as well as the temporal rel ationships between them. The main emphasis (if the paper is on the abstract muscle model, along with limited discussion on the automatic cloning proce ss and higher-level animation control aspects.