PCB-RandNet: Rethinking Random Sampling for LIDAR Semantic Segmentation in Autonomous Driving Scene

TL;DR

This paper introduces PCB-RandNet, a novel sampling method and loss function that improve LiDAR semantic segmentation in autonomous driving by addressing distribution imbalance issues in point cloud data.

Contribution

It proposes a Polar Cylinder Balanced Random Sampling method and a sampling consistency loss to enhance segmentation performance under uneven point distributions.

Findings

Achieves 2.8% and 4.0% performance improvements on SemanticKITTI and SemanticPOSS.

Effectively balances point cloud distributions for better segmentation.

Reduces model variance across different sampling strategies.

Abstract

Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods mainly choose to adopt Random Sampling strategy to process large-scale point clouds. However, our quantative and qualitative studies have found that Random Sampling may be less suitable for the autonomous driving scenario, since the LiDAR points follow an uneven or even long-tailed distribution across the space, which prevents the model from capturing sufficient information from points in different distance ranges and reduces the model's learning capability. To alleviate this problem, we propose a new Polar Cylinder Balanced Random Sampling method that enables the downsampled point clouds to maintain a more balanced distribution and improve the segmentation performance under different spatial distributions. In addition, a sampling consistency loss is introduced to further improve the segmentation performance and reduce the model's variance under different sampling methods. Extensive experiments confirm that our approach produces excellent performance on both SemanticKITTI and SemanticPOSS benchmarks, achieving a 2.8% and 4.0% improvement, respectively. The source code is available at https://github.com/huixiancheng/PCB-RandNet.