ON VIEW LIKELIHOOD AND STABILITY

We define two measures on views: view likelihood and view stability. V iew likelihood measures the probability that a certain view of a given 3D object is observed; it may be used to identity typical, or ''chara cteristic,'' views. View stability measures how little the image chang es as the viewpoint is slightly perturbed; it may be used to identify ''generic'' views. Both definitions are shown to be identical up to th e prior probability of camera orientations, and determined by the 2D m etric used to compare images. We analytically derive the stability and likelihood measures for two feature-based 2D metrics, where the most stable and most likely view is shown to be the flattest view of the 3D shape. Incorporating view likelihood or stability in 3D object recogn ition and 3D reconstruction increases the chance of robust performance . In particular, we propose to use these measures to enhance 3D object recognition and 3D reconstruction algorithms, by adding a second step where the most likely solution is selected among all feasible solutio ns. These applications are demonstrated using simulated and real image s.