Title
WGNet: Wider graph convolution networks for 3D point cloud classification with local dilated connecting and context-aware
Abstract
•A local dilated connecting (LDC) module is presented to generate the adjacency matrix for a graph, which expand the receptive field of graph convolution to encode more information.•To extract the node features as the initial input of GCNs, a context information aware (CIA) module is designed to embed the distribution characteristics of its neighborhood points and its local dimension features, resulting in rich distribution pattern awareness.•A wider and efficient skip-connection-based GCNs combined with LDC and CIA modules is proposed to mine richer features to compensate the insufficiency on the depth of GCNs.
Year
DOI
Venue
2022
10.1016/j.jag.2022.102786
International Journal of Applied Earth Observation and Geoinformation
Keywords
DocType
Volume
3D point cloud,Graph convolution networks,3D object classification,Dilated connecting,Context information aware
Journal
110
ISSN
Citations 
PageRank 
1569-8432
0
0.34
References 
Authors
0
9
Name
Order
Citations
PageRank
Yiping Chen1167.69
Zhipeng Luo200.68
Wen Li300.68
Haojia Lin400.34
Abdul Nurunnabi500.34
Yaojin Lin600.34
Cheng Wang711829.56
Xiao-Ping Zhang800.68
Jonathan Li9798119.18