We propose a new approach for integrating geometric scene knowledge into a level-set tracking framework. Our approach is based on a novel constrained-homography transformation mode...
Visual and inertial sensors, in combination, are able to provide accurate motion estimates and are well-suited for use in many robot navigation tasks. However, correct data fusion...
Abstract This paper presents a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other state of the art meth...
Pushmeet Kohli, Jonathan Rihan, Matthieu Bray, Phi...
Abstract. In the matching tasks which form an integral part of all types of tracking and geometrical vision, there are invariably priors available on the absolute and/or relative i...
We propose an algorithm for estimating disparity and occlusion in stereo video sequences. The algorithm defines a prior on sequences of disparity maps using a 3D Markov random fie...
Oliver M. C. Williams, Michael Isard, John MacCorm...