Neighbourhood Consensus Networks

Authors:
Ignacio Rocco Inria
Mircea Cimpoi CIIRC, CTU Prague
Relja Arandjelović DeepMind
Akihiko Torii Tokyo Institute of Technology, Japan
Tomas Pajdla Czech Technical University in Prague
Josef Sivic Inria and Czech Technical University

Introduction:

The authors address the problem of finding reliable dense correspondences between a pair of images.

Abstract:

We address the problem of finding reliable dense correspondences between a pair of images. This is a challenging task due to strong appearance differences between the corresponding scene elements and ambiguities generated by repetitive patterns. The contributions of this work are threefold. First, inspired by the classic idea of disambiguating feature matches using semi-local constraints, we develop an end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible correspondences between a pair of images without the need for a global geometric model. Second, we demonstrate that the model can be trained effectively from weak supervision in the form of matching and non-matching image pairs without the need for costly manual annotation of point to point correspondences.Third, we show the proposed neighbourhood consensus network can be applied to a range of matching tasks including both category- and instance-level matching, obtaining the state-of-the-art results on the PF Pascal dataset and the InLoc indoor visual localization benchmark.

You may want to know: