Example Based Image Synthesis of Articulated Figures
1801C Page Mill Road
Palo Alto CA 94304
Click here for a compressed PostScript version of this report ]
Click here for a PDF version of this report ]
We present a method for learning complex appearance mappings, such as occur
with images of articulated objects. Traditional interpolation networks
fail on this case since appearance is not necessarily a smooth function
nor a linear manifold for articulated objects. We define an appearance
mapping from examples by constructing a set of independently smooth interpolation
networks; these networks can cover overlapping regions of parameter space.
A set growing procedure is used to find example clusters which are well-approximated
within their convex hull; interpolation then proceeds only within these
sets of examples. With this method physically valid images are produced
even in regions of parameter space where nearby examples have different
appearances. We show results generating both simulated and real arm images.
To appear, Advances in Neural Information Processing Systems 11,
(NIPS '98), MIT Press.
©1998 Interval Research Corp.