Adaptive Graph Convolution for Point Cloud Analysis

This repository contains the implementation of AdaptConv for point cloud analysis.

Adaptive Graph Convolution (AdaptConv) is a point cloud convolution operator presented in our ICCV2021 paper. If you find our work useful in your research, please cite our paper.


  • The code has been tested on one configuration:

    • PyTorch 1.1.0, CUDA 10.1
  • Install required packages:

    • numpy
    • h5py
    • scikit-learn
    • matplotlib


Part Segmentation

Indoor Segmentation

coming soon