Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00163102" target="_blank" >RIV/68407700:21230/09:00163102 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets

Popis výsledku v původním jazyce

This paper presents a new efficient technique for large-scale structure from motion from unordered data sets. We avoid costly computation of all pairwise matches and geometries by sampling pairs of images using the pairwise similarity scores based on thedetected occurrences of visual words leading to a significant speedup. Furthermore, atomic 3D models reconstructed from camera triplets are used as the seeds which form the final large-scale 3D model when merged together. Using three views instead of two allows us to reveal most of the outliers of pairwise geometries at an early stage of the process hindering them from derogating the quality of the resulting 3D structure at later stages. The accuracy of the proposed technique is shown on a set of 64 images where the result of the exhaustive technique is known. Scalability is demonstrated on a landmark reconstruction from hundreds of images.

Název v anglickém jazyce

Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets

Popis výsledku anglicky

This paper presents a new efficient technique for large-scale structure from motion from unordered data sets. We avoid costly computation of all pairwise matches and geometries by sampling pairs of images using the pairwise similarity scores based on thedetected occurrences of visual words leading to a significant speedup. Furthermore, atomic 3D models reconstructed from camera triplets are used as the seeds which form the final large-scale 3D model when merged together. Using three views instead of two allows us to reveal most of the outliers of pairwise geometries at an early stage of the process hindering them from derogating the quality of the resulting 3D structure at later stages. The accuracy of the proposed technique is shown on a set of 64 images where the result of the exhaustive technique is known. Scalability is demonstrated on a landmark reconstruction from hundreds of images.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA201%2F07%2F1136" target="_blank" >GA201/07/1136: Matematika neurčitosti</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2009

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVPR 2009: Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ISBN

978-1-4244-3991-1

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

Omnipress

Místo vydání

Madison

Místo konání akce

Fontainebleau Resort, Miami Beach, Florida

Datum konání akce

20. 6. 2009

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000279038001176