In this paper we present a novel approach to mobile robot navigation in natural unstructured environments. Natural scenes can be considered as random fields where a large number ...
— This paper describes a probabilistic framework for navigation using only appearance data. By learning a generative model of appearance, we can compute not only the similarity o...
This paper addresses the problem of remapping the disparity range of stereoscopic images and video. Such operations are highly important for a variety of issues arising from the p...
Manuel Lang, Alexander Hornung, Oliver Wang, Steve...
Abstract. Recent successful SLAM methods employ hybrid map representations combining the strengths of topological maps and occupancy grids. Such representations often facilitate mu...
Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approac...
Graham Taylor, Ian Spiro, Rob Fergus, Christoph Br...