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

Department of Computer Science

2 Citations (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.

Original language	English
Title of host publication	2012 21st International Conference on Pattern Recognition (ICPR)
Number of pages	4
Publisher	IEEE
Publication date	2012
Pages	2673-2676
ISBN (Print)	978-1-4673-2216-4
Publication status	Published - 2012
Event	21st International Conference on Pattern Recognition - Tsukuba Science City, Japan Duration: 11 Nov 2012 → 15 Nov 2012 Conference number: 21

Conference

Conference	21st International Conference on Pattern Recognition
Number	21
Country/Territory	Japan
City	Tsukuba Science City
Period	11/11/2012 → 15/11/2012

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

Access to Document

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

Cite this

Ylimaki, M, Kannala, J, Holappa, J, Heikkilä, J & Brandt, SS 2012, Robust and accurate multi-view reconstruction by prioritized matching. in 2012 21st International Conference on Pattern Recognition (ICPR). IEEE, pp. 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 -