PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization [article]

Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark, Bo Yang, Andrew Markham, Niki Trigoni
2021 arXiv   pre-print
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map. Compared to RGB image-based relocalization, LiDAR frames can provide rich and robust geometric information about a scene. However, LiDAR point clouds are unordered and unstructured making it difficult to apply traditional deep learning regression models for this task. We address
more » ... this issue by proposing a novel PointNet-style architecture with self-attention to efficiently estimate 6-DoF poses from 360 LiDAR input frames.Extensive experiments on recently released challenging Oxford Radar RobotCar dataset and real-world robot experiments demonstrate that the proposedmethod can achieve accurate relocalization performance.
arXiv:2003.02392v3 fatcat:otfe45l3rza5nkashcwyf72ree