Skip to content

amzn/basis-point-sets

Efficient Learning on Point Clouds with Basis Point Sets

Basis Point Set (BPS) is a simple and efficient method for encoding 3D point clouds into fixed-length representations.

It is based on a simple idea: select k fixed points in space and compute vectors from these basis points to the nearest points in a point cloud; use these vectors (or simply their norms) as features:

Teaser Image

The basis points are kept fixed for all the point clouds in the dataset, providing a fixed representation of every point cloud as a vector. This representation can then be used as input to arbitrary machine learning methods, in particular it can be used as input to off-the-shelf neural networks.

Below is the example of a simple model using BPS features as input for the task of mesh registration over a noisy scan:

Teaser Image

FAQ: what are the key differences between standard occupancy voxels, TSDF and the proposed BPS representation?

  • continuous global vectors instead of simple binary flags or local distances in the cells;
  • smaller number of cells required to represent a shape accurately;
  • BPS cell arrangement could be different from a standard rectangular grid, allowing different types of convolutions;
  • significant improvement in performance: simply substituting occupancy voxels with BPS directional vectors results in +9% accuracy improvement of a VoxNet-like 3D-convolutional network on a ModelNet40 classification challenge.

Check our ICCV 2019 paper for more details.

Usage

Requirements

  • Python >= 3.7;
  • scikit-learn >= 0.21;
  • tqdm >= 4.3;
  • PyTorch >= 1.3 (for running provided demos)

Installation

pip3 install git+https://github.com/amzn/basis-point-sets

Code snippet

Converting point clouds to BPS representation takes few lines of code:

import numpy as np
from bps import bps

# batch of 100 point clouds to convert
x = np.random.normal(size=[100, 2048, 3])

# optional point cloud normalization to fit a unit sphere
x_norm = bps.normalize(x)

# option 1: encode with 1024 random basis and distances as features
x_bps_random = bps.encode(x_norm, bps_arrangement='random', n_bps_points=1024, bps_cell_type='dists')

# option 2: encode with 32^3 grid basis and full vectors to nearest points as features
x_bps_grid = bps.encode(x_norm, bps_arrangement='grid', n_bps_points=32**3, bps_cell_type='deltas')
# the following tensor can be provided as input to any Conv3D network:
x_bps_grid = x_bps_grid.reshape([-1, 32, 32, 32, 3])

Demos

Clone the repository and install the dependencies:

git clone https://github.com/amzn/basis-point-sets
cd basis-point-sets
python setup.py install
pip3 install torch h5py

Check one of the provided examples:

  • ModelNet40 3D shape classification with BPS-MLP (~89% accuracy, ~30 minutes of training on a non-GPU MacBook Pro, ~3 minutes of training on Nvidia V100 16gb):
python bps_demos/train_modelnet_mlp.py
  • ModelNet40 3D shape classification with BPS-Conv3D (~92% accuracy, ~120 minutes of training on Nvidia V100 16gb):
python bps_demos/train_modelnet_conv3d.py
  • Human body mesh registration: coming soon.

Citation

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

@inproceedings{prokudin2019efficient,
  title={Efficient Learning on Point Clouds With Basis Point Sets},
  author={Prokudin, Sergey and Lassner, Christoph and Romero, Javier},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={4332--4341},
  year={2019}
}

License

This library is licensed under the MIT-0 License. See the LICENSE file.

About

No description, website, or topics provided.

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages