/OverlapPredator

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

Primary LanguagePythonMIT LicenseMIT

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

This repository 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 implementation using MinkowskiEngine backbone, please check this

For more information, please see the project website

Predator_teaser

Contact

If you have any questions, please let us know:

News

  • 2021-06-02: Fix feature gathering bug in k-nn graph, please see improved performance in this issue. Stay tunned for updates on other experiments!
  • 2021-05-31: Check our video and poster on project page!
  • 2021-03-25: Camera ready is on arXiv! I also gave a talk on Predator(中文), you can find the recording here: Bilibili, Youtube
  • 2021-02-28: MinkowskiEngine-based PREDATOR release
  • 2020-11-30: Code and paper 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

Note: We observe random data loader crashes due to memory issues, if you observe similar issues, please consider reducing the number of workers or increasing CPU RAM. We now released a sparse convolution-based Predator, have a look here!

Requirements

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

git clone https://github.com/overlappredator/OverlapPredator.git
virtualenv predator; source predator/bin/activate
cd OverlapPredator; pip install -r requirements.txt
cd cpp_wrappers; sh compile_wrappers.sh; cd ..

in your working folder.

Datasets and pretrained models

For KITTI dataset, please follow the instruction on KITTI Odometry website to download the KITTI odometry training set.

We provide

  • preprocessed 3DMatch pairwise datasets (voxel-grid subsampled fragments together with their ground truth transformation matrices)
  • raw dense 3DMatch datasets
  • modelnet dataset
  • pretrained models on 3DMatch, KITTI and Modelnet

The preprocessed data and models can be downloaded by running:

sh scripts/download_data_weight.sh

To download raw dense 3DMatch data, please run:

wget --no-check-certificate --show-progress https://share.phys.ethz.ch/~gsg/pairwise_reg/3dmatch.zip
unzip 3dmatch.zip

The folder is organised as follows:

  • 3dmatch
    • train
      • 7-scenes-chess
        • fragments
          • cloud_bin_*.ply
          • ...
        • poses
          • cloud_bin_*.txt
          • ...
      • ...
    • test

3DMatch(Indoor)

Train

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

python main.py configs/train/indoor.yaml

Evaluate

For 3DMatch, to reproduce Table 2 in our main paper, we first extract features and overlap/matachability scores by running:

python main.py configs/test/indoor.yaml

the features together with scores will be saved to snapshot/indoor/3DMatch. The estimation of the transformation parameters using RANSAC can then be carried out using:

for N_POINTS in 250 500 1000 2500 5000
do
  python scripts/evaluate_predator.py --source_path snapshot/indoor/3DMatch --n_points $N_POINTS --benchmark 3DMatch --exp_dir snapshot/indoor/est_traj --sampling prob
done

dependent on n_points used by RANSAC, this might take a few minutes. The final results are stored in snapshot/indoor/est_traj/{benchmark}_{n_points}_prob/result. To evaluate PREDATOR on 3DLoMatch benchmark, please also change 3DMatch to 3DLoMatch in configs/test/indoor.yaml.

Demo

We prepared a small demo, which demonstrates the whole Predator pipeline using two random fragments from the 3DMatch dataset. To carry out the demo, please run:

python scripts/demo.py configs/test/indoor.yaml

The demo script will visualize input point clouds, inferred overlap regions, and point cloud aligned with the estimated transformation parameters:

demo

ModelNet(Synthetic)

Train

To train PREDATOR on ModelNet, please run:

python main.py configs/train/modelnet.yaml

We provide a small script to evaluate Predator on ModelNet test set, please run:

python main.py configs/test/modelnet.yaml

The rotation and translation errors could be better/worse than the reported ones due to randomness in RANSAC.

KITTI(Outdoor)

We provide a small script to evaluate Predator on KITTI test set, after configuring KITTI dataset, please run:

python main.py configs/test/kitti.yaml

the results will be saved to the log file.

Custom dataset

We have a few tips for train/test on custom dataset

  • If it's similar indoor scenes, please run demo.py first to check the generalisation ability before retraining
  • Remember to voxel-downsample the data in your data loader, see kitti.py for reference

Citation

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

@inproceedings{predator,
  title={PREDATOR: Registration of 3D Point Clouds with Low Overlap},
  author={Shengyu Huang and Zan Gojcic and Mikhail Usvyatsov and Andreas Wieser, Konrad Schindler},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition, 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 reviewers, especially reviewer 2 for his/her valuable inputs.