PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

by   Aoran Xiao, et al.

LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously, capture precise geometry of the surrounding environment and are crucial to many autonomous detection and navigation tasks. Though many 3D deep architectures have been developed, efficient collection and annotation of large amounts of point clouds remain one major challenge in the analytic and understanding of point cloud data. This paper presents PolarMix, a point cloud augmentation technique that is simple and generic but can mitigate the data constraint effectively across different perception tasks and scenarios. PolarMix enriches point cloud distributions and preserves point cloud fidelity via two cross-scan augmentation strategies that cut, edit, and mix point clouds along the scanning direction. The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis. The second is instance-level rotation and paste which crops point instances from one LiDAR scan, rotates them by multiple angles (to create multiple copies), and paste the rotated point instances into other scans. Extensive experiments show that PolarMix achieves superior performance consistently across different perception tasks and scenarios. In addition, it can work as plug-and-play for various 3D deep architectures and also performs well for unsupervised domain adaptation.


page 2

page 4


Simulated LiDAR Repositioning: a novel point cloud data augmentation method

We address a data augmentation problem for LiDAR. Given a LiDAR scan of ...

CURL: Continuous, Ultra-compact Representation for LiDAR

Increasing the density of the 3D LiDAR point cloud is appealing for many...

Deep Learning on Point Clouds for False Positive Reduction at Nodule Detection in Chest CT Scans

The paper focuses on a novel approach for false-positive reduction (FPR)...

FinderNet: A Data Augmentation Free Canonicalization aided Loop Detection and Closure technique for Point clouds in 6-DOF separation

We focus on the problem of LiDAR point cloud based loop detection (or Fi...

Ground vehicle mapping of fields using LiDAR to enable prediction of crop biomass

Mapping field environments into point clouds using a 3D LIDAR has the ab...

RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding

Lidars are depth measuring sensors widely used in autonomous driving and...

Practical optimal registration of terrestrial LiDAR scan pairs

Point cloud registration is a fundamental problem in 3D scanning. In thi...

Please sign up or login with your details

Forgot password? Click here to reset