This paper describes a framework for constructing a linear subspace model of image appearance for complex articulated 3D figures such as humans and other animals. A commercial motion capture system provides 3D data that is aligned with images of subjects performing various activities. Portions of a limb's image appearance are seen from multiple views and for multiple subjects. From these partial views, weighted principal component analysis is used to construct a linear subspace representation of the "un-wrapped" image appearance of each limb. The linear sub-spaces provide a generative model of the object appearance that is exploited in a Bayesian particle filtering tracking sys-tem. Results of tracking single limbs and walking humans are presented.