We present a fully-automated method for real-time and marker-free 3D human motion capture. The system computes the 3D shape of the person filmed from a synchronized camera set. We...
We present a system capable of visually detecting pointing gestures and estimating the 3D pointing direction in real-time. We use Hidden Markov Models (HMMs) trained on different ...
Representing articulated objects as a graphical model has gained much popularity in recent years, often the root node of the graph describes the global position and orientation of...
We have developed a novel human face tracking system that operates in real time at the video frame rate without a need for any special hardware. Our approach is based on the use o...
We present a novel fully automatic method for high resolution, non-rigid dense 3D point tracking. High quality dense point clouds of non-rigid geometry moving at video speeds are ...
Yang Wang, Mohit Gupta, Song Zhang 0002, Sen Wang,...