• PointManifold
• • Requirements
  • Point Cloud Classification
  • • Prepare the dataset:
    • Run the training script:
  • Citing PointManifold

PointManifold

This repo is the official PyTorch implementation for PointManifold:Using Manifold Learning for Point Cloud Classification (https://arxiv.org/abs/2010.07215). The codebase is based on AnTao97/dgcnn.pytorch

Tip: The result of point cloud experiment usually faces greater randomness than 2D image. We suggest you run your experiement more than one time and select the best result. Since the code is iterative updated, the performance may not be the same as the public arxiv version. If there are any issues, you can contact to @DinghowYang.

Requirements

• Python 3.7
• PyTorch 1.2
• CUDA 10.0
• Package: glob, h5py, sklearn

Point Cloud Classification

Prepare the dataset:

• Download ModelNet40 to ./data
• Run Dataset_LLE.py to generate LLE feature extraction

Run the training script:

PointManifold_LLE:

sh run_pointmanifold_lle.sh

PointManifold_NNML:

run_pointmanifold_lle.sh

Citing PointManifold

@misc{yang2020pointmanifold,
      title={PointManifold: Using Manifold Learning for Point Cloud Classification}, 
      author={Dinghao Yang and Wei Gao},
      year={2020},
      eprint={2010.07215},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}