Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
Original language description
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.
Czech name
—
Czech description
—
Classification
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)
Result continuities
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)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
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
Number of pages
10
Pages from-to
4667-4676
Publisher name
IEEE Computer Society
Place of publication
USA
Event location
Nashville
Event date
Jun 20, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000739917304084