Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
We present a technique for local image representation that is invariant to viewpoint for scenes with arbitrary non-planar shape. We show that generic viewpoint invariance can be a...
We describe a new technique to extract the boundary of a walking subject, with ability to predict movement in missing frames. This paper uses a level sets representation of the tra...
Muayed S. Al-Huseiny, Sasan Mahmoodi, Mark S. Nixo...
This paper describes a structure from motion and recognition paradigm for generating 3D models from 2D sets of images. In particular we consider the domain of architectural photog...
Anthony R. Dick, Philip H. S. Torr, Simon J. Ruffl...
Abstract. In the field of the architectural heritage, the representation of artefacts, particularly for communication purposes, has benefited from the development of computer-based...