The aim of Optical Motion Capture is to sequentially estimate the true state X of the subject (generally an articulated body) at any time instant tk from a set of data Dk, capture...
We propose a method for removing non-uniform motion blur from multiple blurry images. Traditional methods focus on estimating a single motion blur kernel for the entire image. In ...
We propose a method to find candidate 2D articulated model configurations by searching for locally optimal configurations under a weak but computationally manageable fitness functi...
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 an enhancement to current image-based rendering methods. It suggests that motion consistency can be used in a realtime dynamic rendering system to increase com...