Skip to Main content Skip to Navigation
Journal articles

NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences

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, TSS, InLoc and HPatches benchmarks.
Document type :
Journal articles
Complete list of metadata
Contributor : Ignacio Rocco Connect in order to contact the contributor
Submitted on : Tuesday, January 5, 2021 - 3:45:41 PM
Last modification on : Tuesday, January 11, 2022 - 11:16:06 AM


Files produced by the author(s)




Ignacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomas Pajdla, et al.. NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2020, pp.14. ⟨10.1109/TPAMI.2020.3016711⟩. ⟨hal-03086922v2⟩



Les métriques sont temporairement indisponibles