Robust and accurate multi-view reconstruction by prioritized matching

Markus Ylimaki; Juho Kannala; Jukka Holappa; Janne Heikkilä; Sami Sebastian Brandt

Robust and accurate multi-view reconstruction by prioritized matching

Markus Ylimaki, Juho Kannala, Jukka Holappa, Janne Heikkilä, Sami Sebastian Brandt

Datalogisk Institut

2 Citationer (Scopus)

Abstract

This paper proposes a prioritized matching approach for finding corresponding points in multiple calibrated images for multi-view stereo reconstruction. The approach takes a sparse set of seed matches between pairs of views as input and then propagates the seeds to neighboring regions by using a prioritized matching method which expands the most promising seeds first. The output of the method is a three-dimensional point cloud. Unlike previous correspondence growing approaches our method allows to use the best-first matching principle in the generic multi-view stereo setting with arbitrary number of input images. Our experiments show that matching the most promising seeds first provides very robust point cloud reconstructions efficiently with just a single expansion step. A comparison to the current state-of-the-art shows that our method produces reconstructions of similar quality but significantly faster.

Originalsprog	Engelsk
Titel	2012 21st International Conference on Pattern Recognition (ICPR)
Antal sider	4
Forlag	IEEE
Publikationsdato	2012
Sider	2673-2676
ISBN (Trykt)	978-1-4673-2216-4
Status	Udgivet - 2012
Begivenhed	21st International Conference on Pattern Recognition - Tsukuba Science City, Japan Varighed: 11 nov. 2012 → 15 nov. 2012 Konferencens nummer: 21

Konference

Konference	21st International Conference on Pattern Recognition
Nummer	21
Land/Område	Japan
By	Tsukuba Science City
Periode	11/11/2012 → 15/11/2012

Adgang til dokumentet

http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6460716&abstractAccess=no&userType=inst

Citationsformater

Ylimaki, M, Kannala, J, Holappa, J, Heikkilä, J & Brandt, SS 2012, Robust and accurate multi-view reconstruction by prioritized matching. i 2012 21st International Conference on Pattern Recognition (ICPR). IEEE, s. 2673-2676, 21st International Conference on Pattern Recognition, Tsukuba Science City, Japan, 11/11/2012. <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6460716&abstractAccess=no&userType=inst>

@inproceedings{33dbab303c1d44a2bae8f31e41325374,

title = "Robust and accurate multi-view reconstruction by prioritized matching",

abstract = "This paper proposes a prioritized matching approach for finding corresponding points in multiple calibrated images for multi-view stereo reconstruction. The approach takes a sparse set of seed matches between pairs of views as input and then propagates the seeds to neighboring regions by using a prioritized matching method which expands the most promising seeds first. The output of the method is a three-dimensional point cloud. Unlike previous correspondence growing approaches our method allows to use the best-first matching principle in the generic multi-view stereo setting with arbitrary number of input images. Our experiments show that matching the most promising seeds first provides very robust point cloud reconstructions efficiently with just a single expansion step. A comparison to the current state-of-the-art shows that our method produces reconstructions of similar quality but significantly faster.",

keywords = "calibration, computer vision, image matching, image reconstruction, stereo image processing, best-first matching principle, generic multiview stereo setting, multiple calibrated images, multiview stereo reconstruction, point cloud reconstructions, prioritized matching approach, seed match sparse set, three-dimensional point cloud, Accuracy, Cameras, Educational institutions, Image reconstruction, Robustness, Stereo image processing, Surface reconstruction",

author = "Markus Ylimaki and Juho Kannala and Jukka Holappa and Janne Heikkil{\"a} and Brandt, {Sami Sebastian}",

year = "2012",

language = "English",

isbn = "978-1-4673-2216-4",

pages = "2673--2676",

booktitle = "2012 21st International Conference on Pattern Recognition (ICPR)",

publisher = "IEEE",

note = "21st International Conference on Pattern Recognition ; Conference date: 11-11-2012 Through 15-11-2012",

}

TY - GEN

T1 - Robust and accurate multi-view reconstruction by prioritized matching

AU - Ylimaki, Markus

AU - Kannala, Juho

AU - Holappa, Jukka

AU - Heikkilä, Janne

AU - Brandt, Sami Sebastian

N1 - Conference code: 21

PY - 2012

Y1 - 2012

N2 - This paper proposes a prioritized matching approach for finding corresponding points in multiple calibrated images for multi-view stereo reconstruction. The approach takes a sparse set of seed matches between pairs of views as input and then propagates the seeds to neighboring regions by using a prioritized matching method which expands the most promising seeds first. The output of the method is a three-dimensional point cloud. Unlike previous correspondence growing approaches our method allows to use the best-first matching principle in the generic multi-view stereo setting with arbitrary number of input images. Our experiments show that matching the most promising seeds first provides very robust point cloud reconstructions efficiently with just a single expansion step. A comparison to the current state-of-the-art shows that our method produces reconstructions of similar quality but significantly faster.

AB - This paper proposes a prioritized matching approach for finding corresponding points in multiple calibrated images for multi-view stereo reconstruction. The approach takes a sparse set of seed matches between pairs of views as input and then propagates the seeds to neighboring regions by using a prioritized matching method which expands the most promising seeds first. The output of the method is a three-dimensional point cloud. Unlike previous correspondence growing approaches our method allows to use the best-first matching principle in the generic multi-view stereo setting with arbitrary number of input images. Our experiments show that matching the most promising seeds first provides very robust point cloud reconstructions efficiently with just a single expansion step. A comparison to the current state-of-the-art shows that our method produces reconstructions of similar quality but significantly faster.

KW - calibration

KW - computer vision

KW - image matching

KW - image reconstruction

KW - stereo image processing

KW - best-first matching principle

KW - generic multiview stereo setting

KW - multiple calibrated images

KW - multiview stereo reconstruction

KW - point cloud reconstructions

KW - prioritized matching approach

KW - seed match sparse set

KW - three-dimensional point cloud

KW - Accuracy

KW - Cameras

KW - Educational institutions

KW - Image reconstruction

KW - Robustness

KW - Stereo image processing

KW - Surface reconstruction

M3 - Article in proceedings

SN - 978-1-4673-2216-4

SP - 2673

EP - 2676

BT - 2012 21st International Conference on Pattern Recognition (ICPR)

PB - IEEE

T2 - 21st International Conference on Pattern Recognition

Y2 - 11 November 2012 through 15 November 2012

ER -