Point Clouds Learning with Attention-based Graph Convolution Networks

by   Zhuyang Xie, et al.
Southwest Jiaotong University

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification techniques such as the convolution neural network to point clouds analysis directly. To solve this problem, we propose a novel network structure, named Attention-based Graph Convolution Networks (AGCN), to extract point clouds features. Taking the learning process as a message propagation between adjacent points, we introduce an attention mechanism to AGCN for analyzing the relationships between local features of the points. In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network. The proposed network is also extended to an encoder-decoder structure for segmentation tasks. Experimental results show that the proposed network can achieve state-of-the-art performance in both classification and segmentation tasks.


page 8

page 9


Graph-based denoising for time-varying point clouds

Noisy 3D point clouds arise in many applications. They may be due to err...

Graph Structure from Point Clouds: Geometric Attention is All You Need

The use of graph neural networks has produced significant advances in po...

Structure Embedded Nucleus Classification for Histopathology Images

Nuclei classification provides valuable information for histopathology i...

Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling

Geometric deep learning is increasingly important thanks to the populari...

GSECnet: Ground Segmentation of Point Clouds for Edge Computing

Ground segmentation of point clouds remains challenging because of the s...

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

This paper introduces a novel network architecture for the classificatio...

Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN

Recent advances in deep convolutional neural networks (CNNs) have motiva...

Please sign up or login with your details

Forgot password? Click here to reset