This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse netw...
Abstract. In this paper we describe a method for estimating the internal parameters of the left and right cameras associated with a stereo image pair. The stereo pair has known epi...
Gabriela Csurka, David Demirdjian, Andreas Ruf, Ra...
Establishing point correspondences between images is a key step for 3D-shape computation. Nevertheless, shape extraction and point correspondence are treated, usually, as two diffe...
Accurate image correspondence is crucial for estimating multiple-view geometry. In this paper, we present a registration-based method for improving accuracy of the image correspond...
We address the volumetric reconstruction problem that takes as input a series of orthographic multi-energy x-ray images, producing as output a reconstructed model space consisting...
Sang N. Le, Mei Kay Lee, Shamima Banu, Anthony C. ...