Evaluating Deep Learning Methods for Low Resolution Point Cloud Registration in Outdoor Scenarios

Siddique, Arslan; Corsini, Massimiliano; Ganovelli, Fabio; Cignoni, Paolo

Evaluating Deep Learning Methods for Low Resolution Point Cloud Registration in Outdoor Scenarios

Files

187-191.pdf (832.28 KB)

Date

2021

Authors

Siddique, Arslan
Corsini, Massimiliano
Ganovelli, Fabio
Cignoni, Paolo

Publisher

The Eurographics Association

Abstract

Point cloud registration is a fundamental task in 3D reconstruction and environment perception. We explore the performance of modern Deep Learning-based registration techniques, in particular Deep Global Registration (DGR) and Learning Multiview Registration (LMVR), on an outdoor real world data consisting of thousands of range maps of a building acquired by a Velodyne LIDAR mounted on a drone. We used these pairwise registration methods in a sequential pipeline to obtain an initial rough registration. The output of this pipeline can be further globally refined. This simple registration pipeline allow us to assess if these modern methods are able to deal with this low quality data. Our experiments demonstrated that, despite some design choices adopted to take into account the peculiarities of the data, more work is required to improve the results of the registration.

        @inproceedings{10.2312:stag.20211489
,
booktitle = {Smart Tools and Apps for Graphics - Eurographics Italian Chapter Conference
},
editor = {Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele
},
title = {{Evaluating Deep Learning Methods for Low Resolution Point Cloud Registration in Outdoor Scenarios
}},
author = {Siddique, Arslan and 
Corsini, Massimiliano and 
Ganovelli, Fabio and 
Cignoni, Paolo
},
year = {2021
},
publisher = {The Eurographics Association
},
ISSN = {2617-4855
},
ISBN = {978-3-03868-165-6
},
DOI = {10.2312/stag.20211489
}
}