@conference {416,
title = {A GRAPH-CNN FOR 3D POINT CLOUD CLASSIFICATION},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year = {2018},
month = {04/2018},
publisher = {IEEE},
organization = {IEEE},
address = {Calgary},
abstract = {Graph convolutional neural networks (Graph-CNNs) extend traditional
CNNs to handle data that is supported on a graph. Major challenges
when working with data on graphs are that the support set (the
vertices of the graph) do not typically have a natural ordering, and in
general, the topology of the graph is not regular (i.e., vertices do not
all have the same number of neighbors). Thus, Graph-CNNs have
huge potential to deal with 3D point cloud data which has been obtained
from sampling a manifold. In this paper we develop a Graph-
CNN for classifying 3D point cloud data, called PointGCN. The
architecture combines localized graph convolutions with two types
of graph downsampling operations (also known as pooling). By
the effective exploration of the point cloud local structure using the
Graph-CNN, the proposed architecture achieves competitive performance
on the 3D object classification benchmark ModelNet, and our
architecture is more stable than competing schemes.},
keywords = {3D point cloud data, Graph convolutional neural networks, graph signal processing, supervised learning},
url = {https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification},
attachments = {http://networks.ece.mcgill.ca/sites/default/files/A GRAPH-CNN FOR 3D POINT CLOUD CLASSIFICATION.pdf},
author = {Yingxue Zhang and Michael G. Rabbat}
}