: 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...
We study the beneficial effect of side information on the Structure from Motion (SfM) estimation problem. The side information that we consider is measurement of a `reference vect...
We propose a multi-view stereo reconstruction algorithm which recovers urban scenes as a combination of meshes and geometric primitives. It provides a compact model while preservi...
We explore a polar representation of optical flow in which each element of the brightness motion field is represented by its magnitude and orientation instead of its Cartesian p...
This study addresses the problem of unsupervised visual learning. It examines existing popular model order selection criteria before proposes two novel criteria for improving visu...