LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition

TL;DR

LoGG3D-Net introduces a local consistency loss to improve global descriptor learning for 3D place recognition, achieving state-of-the-art results on large-scale benchmarks with real-time performance.

Contribution

The paper proposes a novel local consistency loss in an end-to-end architecture to enhance local feature repeatability and global descriptor quality for 3D place recognition.

Findings

Achieves state-of-the-art F1max scores of 0.939 on KITTI and 0.968 on MulRan.

Operates in near real-time, suitable for practical applications.

Demonstrates improved global descriptor robustness through local feature guidance.

Abstract

Retrieval-based place recognition is an efficient and effective solution for re-localization within a pre-built map, or global data association for Simultaneous Localization and Mapping (SLAM). The accuracy of such an approach is heavily dependent on the quality of the extracted scene-level representation. While end-to-end solutions - which learn a global descriptor from input point clouds - have demonstrated promising results, such approaches are limited in their ability to enforce desirable properties at the local feature level. In this paper, we introduce a local consistency loss to guide the network towards learning local features which are consistent across revisits, hence leading to more repeatable global descriptors resulting in an overall improvement in 3D place recognition performance. We formulate our approach in an end-to-end trainable architecture called LoGG3D-Net. Experiments on two large-scale public benchmarks (KITTI and MulRan) show that our method achieves mean $F1_{max}$ scores of $0.939$ and $0.968$ on KITTI and MulRan respectively, achieving state-of-the-art performance while operating in near real-time. The open-source implementation is available at: https://github.com/csiro-robotics/LoGG3D-Net.