Additionally, high-quality motion capture (mocap) data
and realistic human shape models are two important components for animation generation, each of which involves a specific skeleton definition including the number of joints, the
naming convention, hierarchical relationship and underlying
physical meaning of each joint. Ideally, animation software
can drive a human shape model to move and articulate according to the given mocap data and optimize the deformation of the body surface with natural smoothness, as shown
in Fig. 1. With the development of computer graphics and
the mocap technology, there are plenty of mocap data and
3D human models available for various research activities.
However, due to their different sources, there is a major gap
between the mocap data, shape models and animation software, which often makes animation generation a challenging
task. There are three skeleton definitions involved for animation generation which are from the mocap data, shape
models, and software build-in skeleton. The incompatibility among those skeletons often make synthesized animation
sequences unrealistic, inaccurate or even distorted.