Awesome LiDAR Analysis

Baselines Implementations

Large Scale



Hierachical and other

Paper & Code Repo


Graph Neural Network/Deep Learning for Point Cloud

  1. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
    CVPR, 2017 (citation 2908)
    [Torch Geometric] [Torch Point 3D]
  2. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
    NIPS, 2017 (citation 1748)
    [Torch Geometric] [Torch Point 3D]
  3. Dynamic Graph CNN for Learning on Point Clouds
    ACM Transactions on Graphics 2019 (citation 681)
    [Torch Geometric]
  4. PointCNN: Convolution on x-transformed points
    NIPS 2018 (citation 323)
    [Torch Geometric][Torch Point 3D]
  5. Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
    CVPR 2017 (citation 361)
  6. RGCNN: Regularized Graph CNN for Point Cloud Segmentation
    ACM MM 2018 (citation 50)
  7. Grid-GCN for Fast and Scalable Point Cloud Learning
    CVPR 2020
  8. Graph Attention Convolution for Point Cloud Semantic Segmentation
    CVPR 2019 (citation 36)
  9. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
    (citation 235)
  10. Relation-Shape Convolutional Neural Network for Point Cloud Analysis [arXiv] [CVF]
    CVPR 2019 (citation 80)
    [Official Code][Torch Point 3D]
  11. Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
    CVPR 2020
  12. LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
    CVPR 2020
  13. KPConv: Flexible and Deformable Convolution for Point Clouds
    ICCV 2019 (citation 130)
    [Torch Point 3D]


  1. 2020)
  2. 2019 citation:37)
  3. 2019 citation:2)
  4. 79)
  6. (CVPR2019 citation:51)



test section

Method Task Place holder Implementation
Dynamic Graph CNN classification, segmentation Tensorflow+Pytorch
GACNet classification, segmentation Tensorflow Pytorch
Superpoint Graphs classification Pytorch
PointCNN classification, segmentation Tensorflow Pytorch_geometric