Convolutional neural network architecture for geometric matching

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F17%3A00318971" target="_blank" >RIV/68407700:21730/17:00318971 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/CVPR.2017.12" target="_blank" >http://dx.doi.org/10.1109/CVPR.2017.12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2017.12" target="_blank" >10.1109/CVPR.2017.12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Convolutional neural network architecture for geometric matching

Popis výsledku v původním jazyce

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous in-lier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging Proposal Flow dataset.

Název v anglickém jazyce

Convolutional neural network architecture for geometric matching

Popis výsledku anglicky

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous in-lier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging Proposal Flow dataset.

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

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition

ISBN

978-1-5386-0457-1

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

10

Strana od-do

39-48

Název nakladatele

IEEE Computer Society Press

Místo vydání

—

Místo konání akce

Honolulu

Datum konání akce

21. 7. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000418371400005