This paper describes a novel registration approach that is based on a combination of visual and 3D range information. To identify correspondences, local visual features obtained f...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
Terrain can be approximated by a triangular mesh consisting millions of 3D points. Multiresolution triangular mesh (MTM) structures are designed to support applications that use t...
Current visualization methods of volume angiograms are limited in their ability to display vessel connectivity and depth information readily available in the data set. In this wor...
We present an experiment on depth cues for knot visualization in desktop virtual reality (fishtank VR). We used a within-subjects experiment to investigate stereoscopic visuals an...