PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark +3 more
3/5/2020
cs.RO

Official code: loveoxford/vReLoc (10 stars, last commit 2020-12-17).

Abstract

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 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.

View on arXivView PDF

Code Implementations(1)

loveoxford/vReLocOfficial100%
100Dec 8, 20205 years ago

Cite this paper

@article{wang2020pointloc,
  title  = {PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization},
  author = {Wei Wang and Bing Wang and Peijun Zhao and Changhao Chen and Ronald Clark and Bo Yang and Andrew Markham and Niki Trigoni},
  year   = {2020},
  eprint = {2003.02392},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2003.02392}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2003.02392.svg)](https://codeofpaper.com/paper/2003.02392)

Discussion