Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification

Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on uno...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi-An Li, Li-Yan Wang, Jian Lu
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/8832081
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on unordered 3D point cloud and has achieved favorable performance, such as 86% mean accuracy and 89.2% overall accuracy for classification task, respectively. However, this model fails to consider the fine-grained semantic information of local structure for point cloud. Then, a multiscale receptive fields graph attention network (named after MRFGAT) by means of semantic features of local patch for point cloud is proposed in this paper, and the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet datasets, and results show it achieves state-of-the-art performance in shape classification tasks, such as it outperforms GAPNet (Chen et al.) model by 0.1% in terms of OA and compete with DGCNN (Wang et al.) model in terms of MA.
ISSN:1076-2787
1099-0526