Human body modeling method based on FFD

The example-based method for generating realistic, controllable human models was presented. Users are assisted in automatically generating modifying an example body data by controlling the parameters provided. The examples from the Poser and 3D Max is preprocessed as templates. The modeling method learns from these examples the correlation between the parameters and the body geometry. After this learning process the synthesizer translates the mesh of vertices to the generation of appropriate shape and proportion of the body geometry through free-form deformation method. Finally, we demonstrate our modifier synthesizer for more subtle manipulations of example models. On any synthesized model, the underlying bone and skin structure is properly adjusted. By allowing automatic modification from a set of parameters, our approach may eventually lead to the automatic generation of a variety of population models.