A 3D reconstruction method using PMVS for a limited number of view points

Junichi Hata, Koichi Ito, Takafumi Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Patch-based Multi-View Stereo (PMVS), which is an accurate 3D reconstruction method, can reconstruct the accurate and dense 3D shape from enough number of viewpoints. On the other hand, its accuracy is degraded when using only a limited number of viewpoints. Addressing the above problem, this paper improves the PMVS so as to reconstruct the 3D shape from a limited number of viewpoints. Through a set of experiments, we demonstrate that the proposed method exhibits the efficient performance on 3D reconstruction such difficult situations.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Image Technology, IWAIT 2019
EditorsPhooi Yee Lau, Wen-Nung Lie, Sanun Srisuk, Qian Kemao, Lu Yu, Yung-Lyul Lee, Kazuya Hayase
PublisherSPIE
ISBN (Electronic)9781510627734
DOIs
Publication statusPublished - 2019
EventInternational Workshop on Advanced Image Technology 2019, IWAIT 2019 - Singapore, Singapore
Duration: 2019 Jan 62019 Jan 9

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11049
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceInternational Workshop on Advanced Image Technology 2019, IWAIT 2019
Country/TerritorySingapore
CitySingapore
Period19/1/619/1/9

Keywords

  • 3D reconstruction
  • free-viewpoint image
  • patch-based multi-view stereo
  • phase-only correlation

Fingerprint

Dive into the research topics of 'A 3D reconstruction method using PMVS for a limited number of view points'. Together they form a unique fingerprint.

Cite this