In this paper, we present a system for interactive computation of global illumination in dynamic scenes. Our system uses a novel scheme for caching the results of a high quality p...
Parag Tole, Fabio Pellacini, Bruce Walter, Donald ...
We present a vision system for the 3-D modelbased tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D b...
Subspacefacerecognitionoftensuffersfromtwoproblems:(1)thetrainingsamplesetissmallcompared with the high dimensional feature vector; (2) the performance is sensitive to the subspace...
In this paper we present a graph cuts based active contours (GCBAC) approach to object segmentation problems. Our method is a combination of active contours and the optimization t...
Machine Learning based on the Regularized Least Square (RLS) model requires one to solve a system of linear equations. Direct-solution methods exhibit predictable complexity and s...