We propose a novel approach to point matching under large viewpoint and illumination changes that is suitable for accurate object pose estimation at a much lower computational cos...
We propose a novel exemplar based method to estimate 3D human poses from single images by using only the joint correspondences. Due to the inherent depth ambiguity, estimating 3D ...
We develop a novel method for class-based feature matching across large changes in viewing conditions. The method (called MBE) is based on the property that when objects share a si...
We introduce a GPU-friendly technique that efficiently exploits the highly structured nature of urban environments to ensure rendering quality and interactive performance of city...
Paolo Cignoni, Marco Di Benedetto, Fabio Ganovelli...
During this talk, I will introduce a novel family of contextual measures of similarity between distributions: the similarity between two distributions q and p is measured in the co...
Florent Perronnin (Xerox Research Centre Europe), ...