We describe and demonstrate an algorithm that takes as input an unorganized set of points fx1; : : : ; xng IR3 on or near an unknown manifold M, and produces as output a simplicia...
Hugues Hoppe, Tony DeRose, Tom Duchamp, John Alan ...
We present a novel predictive statistical framework to improve the performance of an Eigen Tracker which uses fast and efficient eigen space updates to learn new views of the obje...
Collecting, analyzing, and sharing information via a hypertext results in the continuous modification of information content over a long period of time. Such tasks will benefit fr...
We introduce a new model for semantic annotation and retrieval from image databases. The new model is based on a probabilistic formulation that poses annotation and retrieval as c...
We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...