/OverlapPredator.Mink

Primary LanguagePython

PREDATOR: Registration of 3D Point Clouds with Low Overlap (CVPR 2021)

This repository provides implementation using sparse convolution backbone. It represents the official implementation of the paper:

PREDATOR: Registration of 3D Point Clouds with Low Overlap

*Shengyu Huang, *Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler
|ETH Zurich | * Equal contribution

For more information, please see the project website

Predator_teaser

Contact

If you have any questions, please let us know:

News

  • 2021-03-12: pre-trained model release
  • 2021-02-28: codebase release

Instructions

This code has been tested on

  • Python 3.8.5, PyTorch 1.7.1, CUDA 11.2, gcc 9.3.0, GeForce RTX 3090/GeForce GTX 1080Ti

Requirements

To create a virtual environment and install the required dependences please run:

git clone https://github.com/ShengyuH/OverlapPredator.Mink.git
virtualenv predator; source predator/bin/activate
cd OverlapPredator.Mink; pip install -r requirements.txt

in your working folder. If you come across problem when installing MinkowskiEngine, please have a look here

Train on 3DMatch(Indoor)

After creating the virtual environment and downloading the datasets, Predator can be trained using:

python main.py configs/train/indoor.yaml

Citation

If you find this code useful for your work or use it in your project, please consider citing:

@article{huang2020predator,
  title={PREDATOR: Registration of 3D Point Clouds with Low Overlap},
  author={Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler},
  journal={CVPR},
  year={2021}
}

Acknowledgments

In this project we use (parts of) the official implementations of the followin works:

We thank the respective authors for open sourcing their methods. We would also like to thank Reviewer 2 for valuable inputs.