This is an easy implementation for "Rethinking the compositionality of point clouds through regularization in the hyperbolic space"
More details could be found below:
https://github.com/ma-xu/pointMLP-pytorch/tree/main
https://github.com/diegovalsesia/HyCoRe/tree/main
@article{ma2022rethinking,
title={Rethinking network design and local geometry in point cloud: A simple residual MLP framework},
author={Ma, Xu and Qin, Can and You, Haoxuan and Ran, Haoxi and Fu, Yun},
journal={arXiv preprint arXiv:2202.07123},
year={2022}
}
@inproceedings{montanaro2022rethinking,
author = {Montanaro, Antonio and Valsesia, Diego and Magli, Enrico},
booktitle = {Advances in Neural Information Processing Systems},
title = {Rethinking the compositionality of point clouds through regularization in the hyperbolic space},
year = {2022}
}
You need to download the pre-trained model of PointMLP!
You need to update your pre-trained model path based on the scenario.