Fundamental matrix estimation using relative depths

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00380046" target="_blank" >RIV/68407700:21230/25:00380046 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-73209-6_9" target="_blank" >https://doi.org/10.1007/978-3-031-73209-6_9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-73209-6_9" target="_blank" >10.1007/978-3-031-73209-6_9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fundamental matrix estimation using relative depths

Popis výsledku v původním jazyce

We propose a novel approach to estimate the fundamental matrix from point correspondences and their relative depths. Relative depths can be approximated from the scales of local features, which are commonly available or can be obtained from non-metric monocular depth estimates provided by popular deep learning-based methods. This makes the considered problem very relevant. To derive efficient solutions, we explore new geometric constraints on the fundamental matrix with known relative depths and present new algebraic constraints between the fundamental matrix and the translation vector. Using point correspondences and their relative depths, we derive novel efficient minimal solvers for two fully uncalibrated cameras, two cameras with different unknown focal lengths, and two cameras with equal unknown focal lengths, respectively. We propose different variants of these solvers based on the source of the relative depth information. We present detailed analyses and comparisons with state-of-the-art solvers, including results with 86, 306 image pairs from three large-scale datasets

Název v anglickém jazyce

Fundamental matrix estimation using relative depths

Popis výsledku anglicky

We propose a novel approach to estimate the fundamental matrix from point correspondences and their relative depths. Relative depths can be approximated from the scales of local features, which are commonly available or can be obtained from non-metric monocular depth estimates provided by popular deep learning-based methods. This makes the considered problem very relevant. To derive efficient solutions, we explore new geometric constraints on the fundamental matrix with known relative depths and present new algebraic constraints between the fundamental matrix and the translation vector. Using point correspondences and their relative depths, we derive novel efficient minimal solvers for two fully uncalibrated cameras, two cameras with different unknown focal lengths, and two cameras with equal unknown focal lengths, respectively. We propose different variants of these solvers based on the source of the relative depth information. We present detailed analyses and comparisons with state-of-the-art solvers, including results with 86, 306 image pairs from three large-scale datasets

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

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Computer Vision – ECCV 2024, Part LXXI

ISBN

978-3-031-73208-9

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

18

Strana od-do

142-159

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Milano

Datum konání akce

29. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001353702500009