Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

11/19/2020
by   Xinge Zhu, et al.
0

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern while maintaining these inherent properties. Moreover, a point-wise refinement module is introduced to alleviate the interference of lossy voxel-based label encoding. We evaluate the proposed model on two large-scale datasets, i.e., SemanticKITTI and nuScenes. Our method achieves the 1st place in the leaderboard of SemanticKITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4 the proposed 3D framework also generalizes well to LiDAR panoptic segmentation and LiDAR 3D detection.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

page 9

page 10

09/12/2021

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception

State-of-the-art methods for driving-scene LiDAR-based perception (inclu...
08/04/2020

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

State-of-the-art methods for large-scale driving-scene LiDAR semantic se...
04/03/2020

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

LiDAR point-cloud segmentation is an important problem for many applicat...
03/14/2022

LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network

With the rapid advances of autonomous driving, it becomes critical to eq...
11/24/2020

LiDAR-based Panoptic Segmentation via Dynamic Shifting Network

With the rapid advances of autonomous driving, it becomes critical to eq...
01/17/2021

Deep Parametric Continuous Convolutional Neural Networks

Standard convolutional neural networks assume a grid structured input is...
07/03/2021

Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud

In this preliminary work we attempt to apply submanifold sparse convolut...