by Mutian Xu*, Runyu Ding*, Hengshuang Zhao, and Xiaojuan Qi.

This repository is built for the official implementation of:

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds (CVPR2021) [arXiv]

If you find our work useful in your research, please consider citing:

@inproceedings{xu2021paconv,
  title={PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds},
  author={Xu, Mutian and Ding, Runyu and Zhao, Hengshuang and Qi, Xiaojuan},
  booktitle={CVPR},
  year={2021}
}

• All initialization models and trained models are available.
• Provide fast multiprocessing training (nn.parallel.DistributedDataParallel) with official nn.SyncBatchNorm.
• Incorporated with tensorboardX for better visualization of the whole training process.
• Support recent versions of PyTorch.
• Well designed code structures for easy reading and using.

We provide scripts for different point cloud processing tasks:

• Object Classification task on Modelnet40.

• Shape Part Segmentation task on ShapeNetPart.

• Indoor Scene Segmentation task on S3DIS.

You can find the instructions for running these tasks in the above corresponding folders.

The following tables report the current performances on different tasks and datasets. ( * denotes the backbone architectures)

You are welcome to send pull requests or share some ideas with us. Contact information: Mutian Xu (mino1018@outlook.com) or Runyu Ding (ryding@eee.hku.hk).

Our code base is partially borrowed from PointWeb, DGCNN and PointNet++.

20/05/2022:

Our method is officially supported by MMDetection3D for indoor scene segmentation.

PAConv gets competitive performance on ModelNet-C dataset for object classification under corruptions.