Parallel projection z-buffer images are precomputed for a number of preset viewing directions on the unit sphere. Using the depth information, we can reconstruct a 3-D point from e...
This contribution addresses the problem of obtaining photorealistic 3D models of a scene from images alone with a structure-from-motion approach. The 3D scene is observed from mul...
We present a method for live grouping of feature points into persistent 3D clusters as a single camera browses a static scene, with no additional assumptions, training or infrastr...
Images formed by a human face change with viewpoint. A new technique is described for synthesizing images of faces from new viewpoints, when only a single 2D image is available. A...
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...