Hyperspherical Embedding for Point Cloud Completion

[Project Page] [Paper]

This repository contains source code for Hyperspherical Embedding for Point Cloud Completion (CVPR 2023).

Prerequisites

Download the datasets for point cloud completion: ModelNet40, Completion3D, MVP, ShapeNet. Fill in the corresponding data path in run.sh.
Check the docker files in docker/ and build docker image:

cd docker/
./build.sh

Create docker container using one GPU

./run.sh 0

Check the config file cfgs/config.yaml each time you run the experiment.

Training

./train.sh

For multi-task learning: Set the task in cfgs/config.yaml to be a list of the desired tasks. For example, to train on both classification and comletion tasks, set task to be ['classification','completion'].

Evaluation

Keep all the config parameters as training, and set eval to True, and then run:

./train.sh

TensorBoard Visualization

Set the --logdir in tensorboard.sh to be the desired log directory and run:

./tensorboard.sh

Citations

If you find this work useful for your research, please cite HyperPC in your publications.

@InProceedings{Zhang_2023_CVPR,
    author    = {Zhang, Junming and Zhang, Haomeng and Vasudevan, Ram and 
                Johnson-Roberson, Matthew},
    title     = {Hyperspherical Embedding for Point Cloud Completion},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and 
                Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {5323-5332}
}

haomengz/HyperPC