Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F20%3A00347821" target="_blank" >RIV/68407700:21730/20:00347821 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.springerprofessional.de/en/efficient-neighbourhood-consensus-networks-via-submanifold-spars/18555516" target="_blank" >https://www.springerprofessional.de/en/efficient-neighbourhood-consensus-networks-via-submanifold-spars/18555516</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58545-7_35" target="_blank" >10.1007/978-3-030-58545-7_35</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Popis výsledku v původním jazyce

In this work we target the problem of estimating accurately localized correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence problems and propose modifications to overcome their main limitations: large memory consumption, large inference time and poorly localized correspondences. Our proposed modifications can reduce the memory footprint and execution time more than 10x, with equivalent results. This is achieved by sparsifying the correlation tensor containing tentative matches, and its subsequent processing with a 4D CNN using submanifold sparse convolutions. localization accuracy is significantly improved by processing the input images in higher resolution, which is possible due to the reduced memory footprint, and by a novel two-stage correspondence relocalization module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localization benchmarks, and competitive results on the Aachen Day-Night benchmark.

Název v anglickém jazyce

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Popis výsledku anglicky

In this work we target the problem of estimating accurately localized correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence problems and propose modifications to overcome their main limitations: large memory consumption, large inference time and poorly localized correspondences. Our proposed modifications can reduce the memory footprint and execution time more than 10x, with equivalent results. This is achieved by sparsifying the correlation tensor containing tentative matches, and its subsequent processing with a 4D CNN using submanifold sparse convolutions. localization accuracy is significantly improved by processing the input images in higher resolution, which is possible due to the reduced memory footprint, and by a novel two-stage correspondence relocalization module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localization benchmarks, and competitive results on the Aachen Day-Night benchmark.

Druh

D - Stať ve sborníku

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

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Computer Vision – ECCV 2020, part IX

ISBN

978-3-030-58544-0

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

17

Strana od-do

605-621

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Glasgow

Datum konání akce

23. 8. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—