NCNet : Neighbourhood Consensus Networks for Estimating Image Correspondences

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, i...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 2 vom: 05. Feb., Seite 1020-1034
Auteur principal: Rocco, Ignacio (Auteur)
Autres auteurs: Cimpoi, Mircea, Arandjelovic, Relja, Torii, Akihiko, Pajdla, Tomas, Sivic, Josef
Format: Article en ligne
Langue:English
Publié: 2022
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
Description
Résumé: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
Description:Date Revised 10.01.2022
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2020.3016711