Most existing 3D virtual worlds are basedon a "meeting-space"model, conceived as an extension of textual chat systems. An attractive 3D interface is assumed to be suffici...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
We introduce a new metaphor for learning spatial relations--the 3D puzzle. With this metaphor users learn spatial relations by assembling a geometric model themselves. For this pu...
Bernhard Preim, Felix Ritter, Oliver Deussen, Thom...
Quantitative measurements of changes in evolving brain pathology, such as multiple sclerosis lesions and brain tumors, are important for clinicians to perform pertinent diagnoses a...
Abstract-- We propose a new method for automatically accessing an internet database of 3D models that are searchable only by their user-annotated labels, for using them for vision ...