Example-Based Image Synthesis of Articulated Figures

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. c 1998 Interval Research Corp.

• Type: Conference
• Year: 1998
• Where: NIPS
• Authors: Trevor Darrell
• Keywords: Appearance Mapping, Articulated Objects, Interpolation Networks, NIPS 1998, NIPS 2007