Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps
This addresses localization for autonomous vehicles, presenting a novel method with a new dataset, though it builds on existing self-supervised and Transformer techniques.
The paper tackles the problem of precise 6DoF localization for autonomous vehicles using LiDAR data by introducing a self-supervised learning method with Transformers, achieving state-of-the-art results on datasets like Perth-WA and Appollo-SouthBay.
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 $360^\circ$ 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 $\sim$4km$^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.