Noisy One-point Homographies are Surprisingly Good

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00380042" target="_blank" >RIV/68407700:21230/24:00380042 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR52733.2024.00490" target="_blank" >https://doi.org/10.1109/CVPR52733.2024.00490</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52733.2024.00490" target="_blank" >10.1109/CVPR52733.2024.00490</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Noisy One-point Homographies are Surprisingly Good

Popis výsledku v původním jazyce

Two-view homography estimation is a classic and fundamental problem in computer vision. While conceptually simple, the problem quickly becomes challenging when multiple planes are visible in the image pair. Even with correct matches, each individual plane (homography) might have a very low number of inliers when comparing to the set of all correspondences. In practice, this requires a large number of RANSAC iterations to generate a good model hypothesis. The current state-of-the-art methods therefore seek to reduce the sample size, from four point correspondences originally, by including additional information such as keypoint orientation/angles or local affine information. In this work, we continue in this direction and propose a novel one-point solver that leverages different approximate constraints derived from the same auxiliary information. In experiments we obtain state-of-the-art results, with execution time speed-ups, on large benchmark datasets and show that it is more beneficial for the solver to be sample efficient compared to generating more accurate homographies.

Název v anglickém jazyce

Noisy One-point Homographies are Surprisingly Good

Popis výsledku anglicky

Two-view homography estimation is a classic and fundamental problem in computer vision. While conceptually simple, the problem quickly becomes challenging when multiple planes are visible in the image pair. Even with correct matches, each individual plane (homography) might have a very low number of inliers when comparing to the set of all correspondences. In practice, this requires a large number of RANSAC iterations to generate a good model hypothesis. The current state-of-the-art methods therefore seek to reduce the sample size, from four point correspondences originally, by including additional information such as keypoint orientation/angles or local affine information. In this work, we continue in this direction and propose a novel one-point solver that leverages different approximate constraints derived from the same auxiliary information. In experiments we obtain state-of-the-art results, with execution time speed-ups, on large benchmark datasets and show that it is more beneficial for the solver to be sample efficient compared to generating more accurate homographies.

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/GM22-23183M" target="_blank" >GM22-23183M: Nová generace algoritmů pro řešení problémů geometrie kamer</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-5301-3

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

5125-5134

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Seattle

Datum konání akce

16. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001322555905050