TR2018-041

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling


    •  Shen, Y., Feng, C., Yang, Y., Tian, D., "Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
      BibTeX TR2018-041 PDF Software
      • @inproceedings{Shen2018jun,
      • author = {Shen, Yiru and Feng, Chen and Yang, Yaoqing and Tian, Dong},
      • title = {Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2018,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2018-041}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

Unlike on images, semantic learning on 3D point clouds using a deep network is challenging due to the naturally unordered data structure. Among existing works, Point-Net has achieved promising results by directly learning on point sets. However, it does not take full advantage of a points local neighborhood that contains fine-grained structural information which turns out to be helpful towards better semantic learning. In this regard, we present two new operations to improve PointNet with a more efficient exploitation of local structures. The first one focuses on local 3D geometric structures. In analogy to a convolution kernel for images, we define a point-set kernel as a set of learnable 3D points that jointly respond to a set of neighboring data points according to their geometric affinities measured by kernel correlation, adapted from a similar technique for point cloud registration. The second one exploits local high-dimensional feature structures by recursive feature aggregation on a nearest-neighbor-graph computed from 3D positions. Experiments show that our network can efficiently capture local information and robustly achieve better performances on major datasets. Our code is available at http://www.merl.com/research/license#KCNet

 

  • Software Download