RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

11/25/2019
by   Qingyong Hu, et al.
13

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.

READ FULL TEXT

page 4

page 7

page 13

page 14

page 15

page 16

research
01/30/2022

MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds

Semantic segmentation of 3D point cloud is an essential task for autonom...
research
04/03/2023

Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework

We study the problem of semantic segmentation of large-scale 3D point cl...
research
08/15/2019

PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation

In this paper, we present the PS^2-Net -- a locally and globally aware d...
research
02/22/2022

Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

This paper introduces a novel network architecture for the classificatio...
research
12/17/2020

FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling

This work presents FG-Net, a general deep learning framework for large-s...
research
02/13/2018

Recurrent Slice Networks for 3D Segmentation on Point Clouds

In this paper, we present a conceptually simple and powerful framework, ...
research
09/23/2021

Multi-resolution deep learning pipeline for dense large scale point clouds

Recent development of 3D sensors allows the acquisition of extremely den...

Please sign up or login with your details

Forgot password? Click here to reset