DenseMatch: a dataset for real-time 3D reconstruction

Marco Lombardi; Mattia Savardi; Alberto Signoroni

doi:10.1016/j.dib.2021.107476

DenseMatch: a dataset for real-time 3D reconstruction

Data Brief. 2021 Oct 14:39:107476. doi: 10.1016/j.dib.2021.107476. eCollection 2021 Dec.

Authors

Marco Lombardi¹, Mattia Savardi¹, Alberto Signoroni¹

Affiliation

¹ Information Engineering Department, University of Brescia - Via Branze 38, Brescia 25123, Italy.

Abstract

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.

Keywords: 3D registration; Benchmark dataset; Point-based; Real-time 3D reconstruction.