We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
This paper addresses the problem of vision-based navigation and proposes an original control law to perform such navigation. The overall approach is based on an appearance-based r...
Characterizing the performance of image segmentation approaches has been a persistent challenge. Performance analysis is important since segmentation algorithms often have limited ...
Simon K. Warfield, Kelly H. Zou, William M. Wells ...
Abstract. This paper describes methods of extracting region boundaries from the frames of an image sequence by combining information from spatial or temporal cooccurrence matrices ...
We present a novel method to estimate an approximation of the reflectance characteristics of optically thick, homogeneous translucent materials using only a single photograph as ...