Facial Deformations for MPEG-4
نویسندگان
چکیده
The new MPEG-4 standard, scheduled to become an International Standard in February 1999, will include support not only for natural video and audio, but also for synthetic graphics and sounds. In particular, representation of human faces and bodies will be supported. In the current draft specification of the standard [MPEG-N1901, MPEG-N1902] Facial Animation Parameters (FAPs) and Facial Definition Parameters (FDPs) are defined. FAPs are used to control facial animation at extremely low bitrates (approx. 2 kbit/sec). FDPs are used to define the shape of the face by deforming a generic facial model, or by supplying a substitute model. We present algorithms to interpret the part of FDPs dealing with the deformation of a generic facial model, leading to a personalisation of the model. The implementation starts from a generic model, which is deformed in order to fit the input parameters. The input parameters must include the facial feature points, and may optionally include texture coordinates, and a calibration face model. We apply a cylindrical projection to the generic face in order to interpolate any missing feature points and to fit the texture, if supplied. Then we use a Dirichlet Free Form Deformation [Moccozet 97] interpolation method to deform the generic head according to the set of feature points. If the calibration face model is present, the fitting method is based on cylindrical projections matching and barycentric coordinates to interpolate the non-feature points.
منابع مشابه
Real-Time Speech-Driven Face Animation
This chapter presents our research on real-time speech-driven face animation. First, a visual representation, called Motion Unit (MU), for facial deformation is learned from a set of labeled face deformation data. A facial deformation can be approximated by a linear combination of MUs weighted by the corresponding MU parameters (MUPs), which are used as the visual features of facial deformation...
متن کاملTowards a Generic Talking Head
We present here a framework for developing a generic talking head capable of reproducing the anatomy and the facial deformations induced by speech movements with a set of a few parameters. We will show that the speakerspecific articulatory movements can be straightforward encoded into the normalized MPEG-4 Facial Animation Parameters and Facial Definition Parameters.
متن کاملPlanar Bones for MPEG-4 Facial Animation
This paper proposes a deformation technique called Planar Bones, derived from Surface-oriented Free Form Deformations, and explores its application to the context of Facial Animation. The warping method proposed uses as the control input a polygonal mesh, which is built as a triangulation of the Feature Points defined by MPEG-4. A strong correspondence between the facial geometry and this contr...
متن کاملFast Facial Animation Design for Emotional Virtual Humans
Designing facial animation parameters according to a specific model can be time consuming. In this paper we present a fast approach to design facial animations based on minimal information (only feature points). All facial deformations are automatically computed from MPEG-4 feature points. We also present an extension of this approach that allows to personalize or to customize the deformations ...
متن کاملMPEG-4 facial animation technology: survey, implementation, and results
The emerging MPEG-4 standard specifies an objectbased audiovisual representation framework, integrating both natural and synthetic content. Tools supporting three-dimensional facial animation will be standardized for the first time. To support facial animation decoders with different degrees of complexity, MPEG-4 uses a profiling strategy, which foresees the specification of object types, profi...
متن کامل