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

by   Xinge Zhu, et al.

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, ) often project the point clouds to 2D space and then process them via 2D convolution. Although this cooperation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the 3D 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 pattern while maintaining these inherent properties. The proposed model acts as a backbone and the learned features from this model can be used for downstream tasks such as point cloud semantic and panoptic segmentation or 3D detection. In this paper, we benchmark our model on these three tasks. For semantic segmentation, we evaluate the proposed model on several large-scale datasets, , SemanticKITTI, nuScenes and A2D2. Our method achieves the state-of-the-art on the leaderboard of SemanticKITTI (both single-scan and multi-scan challenge), and significantly outperforms existing methods on nuScenes and A2D2 dataset. Furthermore, the proposed 3D framework also shows strong performance and good generalization on LiDAR panoptic segmentation and LiDAR 3D detection.


page 6

page 7

page 8

page 9

page 10

page 12

page 13

page 14


Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

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

Deformable Filter Convolution for Point Cloud Reasoning

Point clouds are the native output of many real-world 3D sensors. To bor...

Dynamic 3D Scene Analysis by Point Cloud Accumulation

Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robo...

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception

Studying the inherent symmetry of data is of great importance in machine...

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

LiDAR point-cloud segmentation is an important problem for many applicat...

Change of Scenery: Unsupervised LiDAR Change Detection for Mobile Robots

This paper presents a fully unsupervised deep change detection approach ...

Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation

A thorough and holistic scene understanding is crucial for autonomous ve...

Please sign up or login with your details

Forgot password? Click here to reset