We propose a variational bayes approach to the problem of robust estimation of gaussian mixtures from noisy input data. The proposed algorithm explicitly takes into account the un...
In this paper, we present a procedure for organizing real world scenes along semantic axes. The approach is based on the output energies of linear discriminant filters that take i...
We understand and reconstruct special surfaces from 3D data with line geometry methods. Based on estimated surface normals we use approximation techniques in line space to recogniz...
Helmut Pottmann, Michael Hofer, Boris Odehnal, Joh...
This paper proposes a vision-based augmented reality system with correct representation of attached and cast shadows. To realize a seamless augmented reality system, we need to re...
This paper proposes a vision-based augmented reality system with a wide range of registration. To realize an augmented reality system, it is required to geometrically register rea...