TReR: A Lightweight Transformer Re-Ranking Approach for 3D LiDAR Place Recognition

作     者：Barros, Tiago Garrote, Luís Aleksandrov, Martin Premebida, Cristiano Nunes, Urbano J. 

作者机构：The University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Portugal Dahlem Center for Machine Learning and Robotics Freie Universität Berlin Berlin Germany 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Efficiency 

摘      要：Autonomous driving systems often require reliable loop closure detection to guarantee reduced localization drift. Recently, 3D LiDAR-based localization methods have used retrieval-based place recognition to find revisited places efficiently. However, when deployed in challenging real-world scenarios, the place recognition models become more complex, which comes at the cost of high computational demand. This work tackles this problem from an information-retrieval perspective, adopting a first-retrieve-then-re-ranking paradigm, where an initial loop candidate ranking, generated from a 3D place recognition model, is re-ordered by a proposed lightweight transformer-based re-ranking approach (TReR). The proposed approach relies on global descriptors only, being agnostic to the place recognition model. The experimental evaluation, conducted on the KITTI Odometry dataset, where we compared TReR with s.o.t.a. re-ranking approaches such as αQE and SGV, indicate the robustness and efficiency when compared to αQE while offering a good trade-off between robustness and efficiency when compared to SGV. © 2023, CC BY.