Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditions

TL;DR

This paper introduces a label-efficient semi-supervised framework for semantic segmentation of LiDAR point clouds in adverse weather, effectively distinguishing noise from valid points with minimal labeled data.

Contribution

It presents a novel few-shot and semi-supervised learning approach that reduces the need for extensive labeled data in adverse weather LiDAR segmentation.

Findings

Effective detection of snow, fog, and spray in LiDAR data

Competitive performance with significantly less labeled data

Robustness across real and synthetic datasets

Abstract

Adverse weather conditions can severely affect the performance of LiDAR sensors by introducing unwanted noise in the measurements. Therefore, differentiating between noise and valid points is crucial for the reliable use of these sensors. Current approaches for detecting adverse weather points require large amounts of labeled data, which can be difficult and expensive to obtain. This paper proposes a label-efficient approach to segment LiDAR point clouds in adverse weather. We develop a framework that uses few-shot semantic segmentation to learn to segment adverse weather points from only a few labeled examples. Then, we use a semi-supervised learning approach to generate pseudo-labels for unlabelled point clouds, significantly increasing the amount of training data without requiring any additional labeling. We also integrate good weather data in our training pipeline, allowing for high performance in both good and adverse weather conditions. Results on real and synthetic datasets show that our method performs well in detecting snow, fog, and spray. Furthermore, we achieve competitive performance against fully supervised methods while using only a fraction of labeled data.