NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F22%3A00343642" target="_blank" >RIV/68407700:21730/22:00343642 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TPAMI.2020.3016711" target="_blank" >https://doi.org/10.1109/TPAMI.2020.3016711</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2020.3016711" target="_blank" >10.1109/TPAMI.2020.3016711</a>

Jazyk výsledku

angličtina

Název v původním jazyce

NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Inteligentní strojové vnímání</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

1939-3539

Svazek periodika

44

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

1020-1034

Kód UT WoS článku

000740006100034

EID výsledku v databázi Scopus

2-s2.0-85122799504