SphereVLAD++: Attention-based and Signal-enhanced Viewpoint Invariant Descriptor

TL;DR

SphereVLAD++ is an attention-enhanced, viewpoint-invariant 3D place recognition method for LiDAR data, improving localization robustness in autonomous navigation by effectively capturing local-global geometric relationships.

Contribution

The paper introduces SphereVLAD++, a novel attention-based descriptor that enhances viewpoint invariance and signal quality for LiDAR-based localization.

Findings

Outperforms state-of-the-art methods in viewpoint-invariant recognition

Achieves higher successful retrieval rates on KITTI360 and Pittsburgh datasets

Maintains low computational complexity and high efficiency

Abstract

LiDAR-based localization approach is a fundamental module for large-scale navigation tasks, such as last-mile delivery and autonomous driving, and localization robustness highly relies on viewpoints and 3D feature extraction. Our previous work provides a viewpoint-invariant descriptor to deal with viewpoint differences; however, the global descriptor suffers from a low signal-noise ratio in unsupervised clustering, reducing the distinguishable feature extraction ability. We develop SphereVLAD++, an attention-enhanced viewpoint invariant place recognition method in this work. SphereVLAD++ projects the point cloud on the spherical perspective for each unique area and captures the contextual connections between local features and their dependencies with global 3D geometry distribution. In return, clustered elements within the global descriptor are conditioned on local and global geometries and support the original viewpoint-invariant property of SphereVLAD. In the experiments, we evaluated the localization performance of SphereVLAD++ on both public KITTI360 datasets and self-generated datasets from the city of Pittsburgh. The experiment results show that SphereVLAD++ outperforms all relative state-of-the-art 3D place recognition methods under small or even totally reversed viewpoint differences and shows 0.69% and 15.81% successful retrieval rates with better than the second best. Low computation requirements and high time efficiency also help its application for low-cost robots.