The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce ...
Computing correspondences between pairs of images is fundamental to all structures from motion algorithms. Correlation is a popular method to estimate similarity between patches o...
Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown non-rigid mapping and corrupted by clutter an...
Lorenzo Torresani, Vladimir Kolmogorov, Carsten Ro...
Matching local features across images is often useful when comparing or recognizing objects or scenes, and efficient techniques for obtaining image-to-image correspondences have b...
Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature set...