The Roles of Uncertainty in 3D Reconstruction

Philippos Mordohai
Stevens Institute of Technology
Wachman 447
Friday, February 8, 2013 - 11:00

3D reconstruction from two or more images is one of the most well-studied problems in computer vision. Due to the inverse nature of the problem, the reconstructed models typically suffer from various errors. In this talk, I will distinguish between two types of uncertainty that can cause these errors, namely correspondence and geometric uncertainty. The former refers to the uncertainty in determining the correct match for a given pixel while the latter refers to the uncertainty in the coordinates of the reconstructed 3D point, assuming that correct correspondences have been established. Based on this analysis, I will present an approach for depth map fusion and a solution to the next-best-view problem in target localization that benefit from explicit uncertainty modeling.