Two-View Matching with View Synthesis Revisited

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212526" target="_blank" >RIV/68407700:21230/13:00212526 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Two-View Matching with View Synthesis Revisited

Popis výsledku v původním jazyce

Wide-baseline matching, focussing on challenging problems e.g. with extreme viewpoint change,is considered. We introduce the use of view synthesis with affine-covariant detectors to solve such problems and show that matching with the Hessian-Affine or MSER detectors outperforms the state-of-the-art ASIFT. To minimise the loss of speed caused by view synthesis, we propose the Matching On Demand with view Synthesis algorithm (MODS) that uses progressively more synthesized images and more (time-consuming)detectors until reliable estimation of geometry is possible. We show experimentally that the MODS algorithm solves matching problems beyond the state-of-the-art and yet is comparable in speed to standard wide-baseline matchers on simpler problems. Minorcontributions include an improved method for tentative correspondence selection, applicable both with and without view synthesis and a discovery of a view synthesis set up greatly improving MSER robustness to blur and scale change that in

Název v anglickém jazyce

Two-View Matching with View Synthesis Revisited

Popis výsledku anglicky

Wide-baseline matching, focussing on challenging problems e.g. with extreme viewpoint change,is considered. We introduce the use of view synthesis with affine-covariant detectors to solve such problems and show that matching with the Hessian-Affine or MSER detectors outperforms the state-of-the-art ASIFT. To minimise the loss of speed caused by view synthesis, we propose the Matching On Demand with view Synthesis algorithm (MODS) that uses progressively more synthesized images and more (time-consuming)detectors until reliable estimation of geometry is possible. We show experimentally that the MODS algorithm solves matching problems beyond the state-of-the-art and yet is comparable in speed to standard wide-baseline matchers on simpler problems. Minorcontributions include an improved method for tentative correspondence selection, applicable both with and without view synthesis and a discovery of a view synthesis set up greatly improving MSER robustness to blur and scale change that in

Druh

O - Ostatní výsledky

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2013

Kód důvěrnosti údajů

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