Convolutional neural network architecture for geometric matching

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Convolutional neural network architecture for geometric matching

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

<a href="/en/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Intelligent Machine Perception</a><br>

Continuities

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

Publication year

2017

Confidentiality

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

Article name in the collection

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

—

Number of pages

10

Pages from-to

39-48

Publisher name

IEEE Computer Society Press

Place of publication

—

Event location

Honolulu

Event date

Jul 21, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000418371400005