Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00356122" target="_blank" >RIV/68407700:21730/21:00356122 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR46437.2021.00464" target="_blank" >https://doi.org/10.1109/CVPR46437.2021.00464</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR46437.2021.00464" target="_blank" >10.1109/CVPR46437.2021.00464</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

Popis výsledku v původním jazyce

The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottle-neck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores. Patch2Pix is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without retraining, which leads us to state-of-the-art localization performance.

Název v anglickém jazyce

Patch2Pix: Epipolar-Guided Pixel-Level Correspondences

Popis výsledku anglicky

The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottle-neck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores. Patch2Pix is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without retraining, which leads us to state-of-the-art localization performance.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

978-1-6654-4509-2

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

4667-4676

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Nashville

Datum konání akce

20. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000739917304084