A simple stereo matching algorithm is proposed that visits only a small fraction of disparity space in order to find a semi-dense disparity map. It works by growing from a small s...
We propose a method for learning using a set of feature representations which retrieve different amounts of information at different costs. The goal is to create a more efficient ...
Anelia Angelova, Larry Matthies, Daniel M. Helmick...
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitabl...
We study the beneficial effect of side information on the Structure from Motion (SfM) estimation problem. The side information that we consider is measurement of a `reference vect...
In this paper we propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that ...