This page is provided for historical and archival purposes only. While the seminar dates are correct, we offer no guarantee of informational accuracy or link validity. Contact information for the speakers, hosts and seminar committee are certainly out of date.
Stereo vision has traditionally been formulated in terms of an image-based matching process. In spite of the best efforts of some of the greatest minds in computer vision, stereo vision formulated in this way remains unreliable, inaccurate, and inefficient. We have reformulated it in terms of three-dimensional surface extraction. In this formulation stereo vision can be made reliable, accurate, and fast, as will be demonstrated.