DenseMatch: a dataset for real-time 3D reconstruction.

3D registration Benchmark dataset Point-based Real-time 3D reconstruction

Journal

Data in brief
ISSN: 2352-3409
Titre abrégé: Data Brief
Pays: Netherlands
ID NLM: 101654995

Informations de publication

Date de publication:
Dec 2021
Historique:
received: 13 07 2021
revised: 05 10 2021
accepted: 06 10 2021
entrez: 29 10 2021
pubmed: 30 10 2021
medline: 30 10 2021
Statut: epublish

Résumé

We provide a database aimed at real-time quantitative analysis of 3D reconstruction and alignment methods, containing 3140 point clouds from 10 subjects/objects. These scenes are acquired with a high-resolution 3D scanner. It contains depth maps that produce point clouds with more than 500k points on average. This dataset is useful to develop new models and alignment strategies to automatically reconstruct 3D scenes from data acquired with optical scanners or benchmarking purposes.

Identifiants

pubmed: 34712753
doi: 10.1016/j.dib.2021.107476
pii: S2352-3409(21)00757-5
pmc: PMC8529091
doi:

Types de publication

Journal Article

Langues

eng

Pagination

107476

Informations de copyright

© 2021 Published by Elsevier Inc.

Déclaration de conflit d'intérêts

The authors declare that they have no competing financial interests or personal relationships which have, or could be perceived to have, influenced the work reported in this article.

Auteurs

Marco Lombardi (M)

Information Engineering Department, University of Brescia - Via Branze 38, Brescia 25123, Italy.

Mattia Savardi (M)

Information Engineering Department, University of Brescia - Via Branze 38, Brescia 25123, Italy.

Alberto Signoroni (A)

Information Engineering Department, University of Brescia - Via Branze 38, Brescia 25123, Italy.

Classifications MeSH