Corpus ID: 215548288

LightConvPoint: convolution for points

@article{Boulch2020LightConvPointCF,
  title={LightConvPoint: convolution for points},
  author={Alexandre Boulch and Gilles Puy and Renaud Marlet},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.04462}
}
  • Alexandre Boulch, Gilles Puy, Renaud Marlet
  • Published 2020
  • Computer Science
  • ArXiv
  • Recent state-of-the-art methods for point cloud semantic segmentation are based on convolution defined for point clouds. In this paper, we propose a formulation of the convolution for point cloud directly designed from the discrete convolution in image processing. The resulting formulation underlines the separation between the discrete kernel space and the geometric space where the points lies. The link between the two space is done by a change space matrix $\mathbf{A}$ which distributes the… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 58 REFERENCES

    Edge-Convolution Point Net for Semantic Segmentation of Large-Scale Point Clouds

    PointCNN: Convolution On X-Transformed Points

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Tangent Convolutions for Dense Prediction in 3D

    VIEW 1 EXCERPT

    PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    PointCNN: convolution on Χ -transformed points

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    SPLATNet: Sparse Lattice Networks for Point Cloud Processing

    VIEW 2 EXCERPTS

    3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

    VIEW 1 EXCERPT

    Pointwise Convolutional Neural Networks

    VIEW 1 EXCERPT