Log In Sign Up

SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty

by   Gwangtak Bae, et al.

LiDAR is widely used to capture accurate 3D outdoor scene structures. However, LiDAR produces many undesirable noise points in snowy weather, which hamper analyzing meaningful 3D scene structures. Semantic segmentation with snow labels would be a straightforward solution for removing them, but it requires laborious point-wise annotation. To address this problem, we propose a novel self-supervised learning framework for snow points removal in LiDAR point clouds. Our method exploits the structural characteristic of the noise points: low spatial correlation with their neighbors. Our method consists of two deep neural networks: Point Reconstruction Network (PR-Net) reconstructs each point from its neighbors; Reconstruction Difficulty Network (RD-Net) predicts point-wise difficulty of the reconstruction by PR-Net, which we call reconstruction difficulty. With simple post-processing, our method effectively detects snow points without any label. Our method achieves the state-of-the-art performance among label-free approaches and is comparable to the fully-supervised method. Moreover, we demonstrate that our method can be exploited as a pretext task to improve label-efficiency of supervised training of de-snowing.


page 2

page 11


MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds

We present a self-supervised task on point clouds, in order to learn mea...

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks

Recent learning-based LiDAR odometry methods have demonstrated their com...

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

State-of-the-art methods for large-scale driving-scene LiDAR semantic se...

Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

We present a self-supervised learning approach for the semantic segmenta...

Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk

Due to the scarcity of annotated scene flow data, self-supervised scene ...

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Densely annotating LiDAR point clouds is costly, which restrains the sca...

FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding

Projecting the point cloud on the 2D spherical range image transforms th...