Abstract. In this paper we propose a novel variational technique for the knowledge based segmentation of two dimensional objects. One of the elements of our approach is the use of ...
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Standard approaches to stereo correspondence have difficulty when scene structure does not lie in or near the frontal parallel plane, in part because an orientation disparity as we...
We present a Bayesian approach to image-based visual hull reconstruction. The 3-D shape of an object of a known class is represented by sets of silhouette views simultaneously obs...
Kristen Grauman, Gregory Shakhnarovich, Trevor Dar...
Abstract. This paper describes a new method for matching line segments between two images in order to compute the relative camera pose. This approach improves the camera pose for i...
Irene Reisner-Kollmann, Andreas Reichinger, Werner...