3D Point Capsule Networks

@article{Zhao20193DPC,
  title={3D Point Capsule Networks},
  author={Yongheng Zhao and Tolga Birdal and Haowen Deng and Federico Tombari},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={1009-1018}
}
  • Yongheng Zhao, Tolga Birdal, +1 author Federico Tombari
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule networks arise as a direct consequence of our unified formulation of the common 3D auto-encoders. The dynamic routing scheme and the peculiar 2D latent space deployed by our capsule networks bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 36 CITATIONS

    Quaternion Equivariant Capsule Networks for 3D Point Clouds

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    A Rotation-Invariant Framework for Deep Point Cloud Analysis

    VIEW 1 EXCERPT
    CITES METHODS

    Geometric Capsule Autoencoders for 3D Point Clouds

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering

    VIEW 3 EXCERPTS
    CITES METHODS & RESULTS

    Deep Learning for 3D Point Clouds: A Survey

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Fully Convolutional Geometric Features

    DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES

    PU-Net: Point Cloud Upsampling Network

    VIEW 1 EXCERPT

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

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Tangent Convolutions for Dense Prediction in 3D

    VIEW 1 EXCERPT

    VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

    • Yin Zhou, Oncel Tuzel
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    VIEW 1 EXCERPT

    FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention

    VIEW 1 EXCERPT

    OctNet: Learning Deep 3D Representations at High Resolutions

    VIEW 1 EXCERPT

    PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

    VIEW 4 EXCERPTS