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%2F19%3A00329435" target="_blank" >RIV/68407700:21730/19:00329435 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TPAMI.2018.2865351" target="_blank" >https://doi.org/10.1109/TPAMI.2018.2865351</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2018.2865351" target="_blank" >10.1109/TPAMI.2018.2865351</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, homography 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 inlier 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 PF, TSS and Caltech-101 datasets. IEEE

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, homography 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 inlier 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 PF, TSS and Caltech-101 datasets. IEEE

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

2019

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

41

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

2553-2567

Kód UT WoS článku

000489838200002

EID výsledku v databázi Scopus

2-s2.0-85051638908