Constrained viewpoint from occluding contour

The paper addresses the problem of how to constrain the set of viewpoints from which a 3D model will project to a given a set of occluding contour features. The approach is new in that it relies on a precomputed occluding contour representation for polyhedral models that makes T-junctions, contour terminals and the change in contour topology explicit. Potential model-image correspondences of occluding contour features can be formulated as regions in viewpoint space defined by constraint boundaries since features are only visible from a restricted set of viewpoints. The implementation results demonstrate that T-junction features can efficiently constrain the space of viewpoints to produce a small, bounded viewpoint set that accounts for the occluding contour features