FaceSpace: a facial spatial-domain toolkit

We describe a visual development system for exploring "face space", both in terms of facial types and animated expressions. Imagine an n-dimensional space describing every humanoid face, where each dimension represents a different facial characteristic. Within this continuous space, it would be possible to traverse a path from any face to any other face, morphing through faces along that path. It is also possible to combine elements of this space to create an expressive, emotive, talking 3D synthetic face of any given facial type. This development toolkit, called FaceSpace, is based on a hierarchical parametric approach to facial animation and creation. We present our early results on exploring a face space and the relationships between different facial types, as well as creating an additive language of hierarchical expressions, emotions and lip-sync sequences by using combined elements of a facial domain.