Facial modeling and animation has long fascinated computer graphics researchers, not only for the ubiquity of faces in the real world, but also for the inherent problems in creating surface deformations expressive behaviors. Face animation is inherently a multi-disciplinary effort. Within computer graphics, applications of facial simulations have greatly increased as workstation performance permits real-time display of the hundreds of polygons necessary for minimal realism. Recent progress in facial animation now promises to provide useful and capable tools for virtual environments, entertainment, telecommunication, education, linguistics, psychology and medicine. Each of these fields has already applied various sorts of face models to aspects of research: as ``talking heads'', as computer-controllable experiment generators, and as plastic surgery mannequins.
Such a widespread demonstration of interest called for a workshop gathering together researchers in various disciplines such as computer graphics, linguistics and psychology. Noticing the multiplicity and diversity of the current research in this field, we felt the need to have a global view on the actual state-of-the-art and to define one or more ``standards'' in facial models. There has never been any similar forum with this purpose in this field. A relevant forum was held 1992 which was sponsored by the National Science Foundation: Planning Workshop on Facial Expression Understanding. The workshop reported on here looked at establishing a common database of facial expressions and at automatically extracting information from facial activity. This workshop can be viewed as a natural continuation of this first workshop; that is, given the analysis of facial actions, we propose to find common tools to synthesize the extracted data.
The goal of this meeting was to define scientifically defensible, computationally reasonable, and experimentally useful computational facial models as the basis for future research and development. Common facial models within as well as across discipline boundaries will accelerate applications, accessibility, interoperability, and reduce redundant developments, software costs, and animation control incompatibility.
The sponsors of this workshop are: