Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
Created by Ruikai Cui, Shi Qiu, Saeed Anwar, Jing Zhang, Nick Barnes
[arXiv] [poster] [Supplymentry]
To-do
- More instruction coming soon
Usage
Requirements
Building Pytorch Extensions for Chamfer Distance, PointNet++ and kNN
Dataset
Preprocessed 3D-EPN dataset can be downloaded from [Google Drive], [OneDrive]
Place the dataset in ./data/EPN3D/
Training
train the model
python main.py --config ./cfgs/EPN3D_models/ResEBM.yaml --exp_name exp_name
License
MIT License
Acknowledgements
Our code is inspired by PoinTr.
Citation
If you find our work useful in your research, please consider citing:
@inproceedings{cui2022ltupcn,
title={Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion},
author={Cui, Ruikai and Qiu, Shi and Anwar, Saeed and Zhang, Jing and Barnes, Nick},
booktitle={BMVC},
year={2022}
}