TransLoc3D: Point cloud based large-scale place recognition using adaptive receptive fields

Xu, Tian-Xing, Guo, Yuan-Chen, Li, Zhiqiang, Yu, Ge, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Zhang, Song-Hai 2022. TransLoc3D: Point cloud based large-scale place recognition using adaptive receptive fields. Communications in Information and Systems 23 (1) , pp. 57-83. 10.4310/CIS.2023.v23.n1.a3

Full text not available from this repository.

Abstract

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved promising results, existing solutions neglect the following aspects, which may cause performance degradation: (1) huge size difference between objects in outdoor scenes; (2) moving objects that are unrelated to place recognition; (3) long-range contextual information. We illustrate that the above aspects bring challenges to extracting discriminative global descriptors. To mitigate these problems, we propose a novel method named TransLoc3D, utilizing adaptive receptive fields with a pointwise reweighting scheme to handle objects of different sizes while suppressing noises, and an external transformer to capture longrange feature dependencies. As opposed to existing architectures which adopt fixed and limited receptive fields, our method benefits from size-adaptive receptive fields as well as global contextual information, and outperforms current state-of-the-arts with significant improvements on popular datasets.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	International Press
ISSN:	1526-7555
Date of First Compliant Deposit:	13 February 2023
Date of Acceptance:	9 August 2022
Last Modified:	17 May 2023 13:03
URI:	https://orca.cardiff.ac.uk/id/eprint/156940

Actions (repository staff only)

Edit Item