{
  "id": "1812.01711",
  "version": "v1",
  "published": "2018-11-28T17:00:34.000Z",
  "updated": "2018-11-28T17:00:34.000Z",
  "title": "A Graph-CNN for 3D Point Cloud Classification",
  "authors": [
    "Yingxue Zhang",
    "Michael Rabbat"
  ],
  "comment": "Published as a conference paper at ICASSP 2018",
  "categories": [
    "cs.CV",
    "cs.LG",
    "stat.ML"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-11-28T17:00:34.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "3d point cloud classification",
      "3d object classification benchmark modelnet",
      "classifying 3d point cloud data",
      "point cloud local structure"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}