Multi-view 3D reconstruction by random-search and propagation with view-dependent patch maps

Youngjung Uh, Hyeran Byun

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper proposes an efficient multi-view 3D reconstruction method based on randomization and propagation scheme. Our method progressively refines a 3D model of a given scene by randomly perturbing the initial guess of 3D points and propagating photo-consistent ones to their neighbors. While finding local optima is an ordinary method for better photo-consistency, our randomization and propagation takes lucky matchings to spread better points replacing old ones for reducing the computational complexity. Experiments show favorable efficiency of the proposed method accompanied by competitive accuracy with the state-of-the-art methods.

Original languageEnglish
Pages (from-to)16597-16614
Number of pages18
JournalMultimedia Tools and Applications
Volume75
Issue number23
DOIs
Publication statusPublished - 2016 Dec 1

Fingerprint

Computational complexity
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{ac9b0fe2f06e4fa19b9f44d1041d508f,
title = "Multi-view 3D reconstruction by random-search and propagation with view-dependent patch maps",
abstract = "This paper proposes an efficient multi-view 3D reconstruction method based on randomization and propagation scheme. Our method progressively refines a 3D model of a given scene by randomly perturbing the initial guess of 3D points and propagating photo-consistent ones to their neighbors. While finding local optima is an ordinary method for better photo-consistency, our randomization and propagation takes lucky matchings to spread better points replacing old ones for reducing the computational complexity. Experiments show favorable efficiency of the proposed method accompanied by competitive accuracy with the state-of-the-art methods.",
author = "Youngjung Uh and Hyeran Byun",
year = "2016",
month = "12",
day = "1",
doi = "10.1007/s11042-016-3621-x",
language = "English",
volume = "75",
pages = "16597--16614",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "23",

}

Multi-view 3D reconstruction by random-search and propagation with view-dependent patch maps. / Uh, Youngjung; Byun, Hyeran.

In: Multimedia Tools and Applications, Vol. 75, No. 23, 01.12.2016, p. 16597-16614.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-view 3D reconstruction by random-search and propagation with view-dependent patch maps

AU - Uh, Youngjung

AU - Byun, Hyeran

PY - 2016/12/1

Y1 - 2016/12/1

N2 - This paper proposes an efficient multi-view 3D reconstruction method based on randomization and propagation scheme. Our method progressively refines a 3D model of a given scene by randomly perturbing the initial guess of 3D points and propagating photo-consistent ones to their neighbors. While finding local optima is an ordinary method for better photo-consistency, our randomization and propagation takes lucky matchings to spread better points replacing old ones for reducing the computational complexity. Experiments show favorable efficiency of the proposed method accompanied by competitive accuracy with the state-of-the-art methods.

AB - This paper proposes an efficient multi-view 3D reconstruction method based on randomization and propagation scheme. Our method progressively refines a 3D model of a given scene by randomly perturbing the initial guess of 3D points and propagating photo-consistent ones to their neighbors. While finding local optima is an ordinary method for better photo-consistency, our randomization and propagation takes lucky matchings to spread better points replacing old ones for reducing the computational complexity. Experiments show favorable efficiency of the proposed method accompanied by competitive accuracy with the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84975223406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975223406&partnerID=8YFLogxK

U2 - 10.1007/s11042-016-3621-x

DO - 10.1007/s11042-016-3621-x

M3 - Article

AN - SCOPUS:84975223406

VL - 75

SP - 16597

EP - 16614

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 23

ER -