This paper presents a direct and stochastic technique for real time estimation of on board camera position and orientation—the ego-motion problem. An on board stereo vision syste...
In this paper we present a novel method for estimating the object pose for 3D objects with welldefined planar surfaces. Specifically, we investigate the feasibility of estimating...
Ovidiu Ghita, Paul F. Whelan, David Vernon, John M...
This paper addresses the problem of recovering 3D non-rigid shape models from image sequences. For example, given a video recording of a talking person, we would like to estimate ...
Christoph Bregler, Aaron Hertzmann, Henning Bierma...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference...