English

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

Computer Vision and Pattern Recognition 2023-08-15 v2 Artificial Intelligence Machine Learning Robotics

Abstract

Precise localization is critical for autonomous vehicles. We present a self-supervised learning method that employs Transformers for the first time for the task of outdoor localization using LiDAR data. We propose a pre-text task that reorganizes the slices of a 360360^\circ LiDAR scan to leverage its axial properties. Our model, called Slice Transformer, employs multi-head attention while systematically processing the slices. To the best of our knowledge, this is the first instance of leveraging multi-head attention for outdoor point clouds. We additionally introduce the Perth-WA dataset, which provides a large-scale LiDAR map of Perth city in Western Australia, covering \sim4km2^2 area. Localization annotations are provided for Perth-WA. The proposed localization method is thoroughly evaluated on Perth-WA and Appollo-SouthBay datasets. We also establish the efficacy of our self-supervised learning approach for the common downstream task of object classification using ModelNet40 and ScanNN datasets. The code and Perth-WA data will be publicly released.

Keywords

Cite

@article{arxiv.2301.08957,
  title  = {Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps},
  author = {Muhammad Ibrahim and Naveed Akhtar and Saeed Anwar and Michael Wise and Ajmal Mian},
  journal= {arXiv preprint arXiv:2301.08957},
  year   = {2023}
}

Comments

Accepted in IEEE International Conference on Robotics and Automation (ICRA), 2023

R2 v1 2026-06-28T08:16:58.565Z