Abstract

We address the problem of large scale image retrieval in a wide-baseline setting, where for any query image all the matching database images will come from very different viewpoints. In such set- tings traditional bag-of-visual-words approaches are not equipped to han- dle the significant feature descriptor transformations that occur under large camera motions. In this paper we present a novel approach that includes an o?ine step of feature matching which allows us to observe how local descriptors transform under large camera motions. These ob- servations are encoded in a graph in the quantized feature space. This graph can be used directly within a soft-assignment feature quantization scheme for image retrieval.