: This paper proposes a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input imag...
In this article, we present a rule-based language dedicated to topological operations, based on graph transformations. Generalized maps are described as a particular class of graph...
We develop a novel method for fitting high-resolution template meshes to detailed human body range scans with sparse 3D markers. We formulate an optimization problem in which the ...
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...
It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online fea...