Real-time scene reconstruction and triangle mesh generation using multiple RGB-D cameras

Siim Meerits, Vincent Nozick, Hideo Saito

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We present a novel 3D reconstruction system that can generate a stable triangle mesh using data from multiple RGB-D sensors in real time for dynamic scenes. The first part of the system uses moving least squares (MLS) point set surfaces to smooth and filter point clouds acquired from RGB-D sensors. The second part of the system generates triangle meshes from point clouds. The whole pipeline is executed on the GPU and is tailored to scale linearly with the size of the input data. Our contributions include changes to the MLS method for improving meshing, a fast triangle mesh generation method and GPU implementations of all parts of the pipeline.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalJournal of Real-Time Image Processing
DOIs
Publication statusAccepted/In press - 2017 Nov 18

Fingerprint

Mesh generation
Pipelines
Cameras
Sensors
Graphics processing unit

Keywords

  • 3D reconstruction
  • GPU
  • Mesh zippering
  • Meshing
  • RGB-D cameras

ASJC Scopus subject areas

  • Information Systems

Cite this

Real-time scene reconstruction and triangle mesh generation using multiple RGB-D cameras. / Meerits, Siim; Nozick, Vincent; Saito, Hideo.

In: Journal of Real-Time Image Processing, 18.11.2017, p. 1-13.

Research output: Contribution to journalArticle

@article{8a429cc0588945809a31ad39000095b6,
title = "Real-time scene reconstruction and triangle mesh generation using multiple RGB-D cameras",
abstract = "We present a novel 3D reconstruction system that can generate a stable triangle mesh using data from multiple RGB-D sensors in real time for dynamic scenes. The first part of the system uses moving least squares (MLS) point set surfaces to smooth and filter point clouds acquired from RGB-D sensors. The second part of the system generates triangle meshes from point clouds. The whole pipeline is executed on the GPU and is tailored to scale linearly with the size of the input data. Our contributions include changes to the MLS method for improving meshing, a fast triangle mesh generation method and GPU implementations of all parts of the pipeline.",
keywords = "3D reconstruction, GPU, Mesh zippering, Meshing, RGB-D cameras",
author = "Siim Meerits and Vincent Nozick and Hideo Saito",
year = "2017",
month = "11",
day = "18",
doi = "10.1007/s11554-017-0736-x",
language = "English",
pages = "1--13",
journal = "Journal of Real-Time Image Processing",
issn = "1861-8200",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Real-time scene reconstruction and triangle mesh generation using multiple RGB-D cameras

AU - Meerits, Siim

AU - Nozick, Vincent

AU - Saito, Hideo

PY - 2017/11/18

Y1 - 2017/11/18

N2 - We present a novel 3D reconstruction system that can generate a stable triangle mesh using data from multiple RGB-D sensors in real time for dynamic scenes. The first part of the system uses moving least squares (MLS) point set surfaces to smooth and filter point clouds acquired from RGB-D sensors. The second part of the system generates triangle meshes from point clouds. The whole pipeline is executed on the GPU and is tailored to scale linearly with the size of the input data. Our contributions include changes to the MLS method for improving meshing, a fast triangle mesh generation method and GPU implementations of all parts of the pipeline.

AB - We present a novel 3D reconstruction system that can generate a stable triangle mesh using data from multiple RGB-D sensors in real time for dynamic scenes. The first part of the system uses moving least squares (MLS) point set surfaces to smooth and filter point clouds acquired from RGB-D sensors. The second part of the system generates triangle meshes from point clouds. The whole pipeline is executed on the GPU and is tailored to scale linearly with the size of the input data. Our contributions include changes to the MLS method for improving meshing, a fast triangle mesh generation method and GPU implementations of all parts of the pipeline.

KW - 3D reconstruction

KW - GPU

KW - Mesh zippering

KW - Meshing

KW - RGB-D cameras

UR - http://www.scopus.com/inward/record.url?scp=85034212601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034212601&partnerID=8YFLogxK

U2 - 10.1007/s11554-017-0736-x

DO - 10.1007/s11554-017-0736-x

M3 - Article

SP - 1

EP - 13

JO - Journal of Real-Time Image Processing

JF - Journal of Real-Time Image Processing

SN - 1861-8200

ER -