This is our implementation of PointCleannet, a network removes outliers and reduces noise in unordered point clouds.
The architecture is similar to PCPNet (with a few smaller modifications).
This code was written by Marie-Julie Rakotosaona, based on the excellent implementation of PCPNet by Paul Guerrero and Yanir Kleiman.
Install required python packages, if they are not already installed (tensorboardX is only required for training):
pip install numpy
pip install scipy
pip install tensorboardX
Clone this repository:
git clone https://github.com/mrakotosaon/pointcleannet.git
cd pointcleannet
Download datasets:
cd data
python download_data.py --task denoising
python download_data.py --task outliers_removal
Download pretrained models:
cd models
python download_models.py --task denoising
python download_models.py --task outliers_removal
Our data can be found here: https://nuage.lix.polytechnique.fr/index.php/s/xSRrTNmtgqgeLGa .
It contains the following files:
In the datasets the input and ground truth point clouds are stored in different files with the same name but with different extensions.
.xyz
for input noisy point clouds, .clean_xyz
for the ground truth..xyz
for input point clouds with outliers, .outliers
for the labels.To classify outliers using default settings:
cd outliers_removal
mkdir results
python eval_pcpnet.py
To denoise point clouds using default settings:
cd noise_removal
mkdir results
./run.sh
(the input shapes and number of iterations are specified in run.sh file)
To train PCPNet with the default settings:
python train_pcpnet.py
If you use our work, please cite our paper.
@inproceedings{rakotosaona2020pointcleannet,
title={POINTCLEANNET: Learning to denoise and remove outliers from dense point clouds},
author={Rakotosaona, Marie-Julie and La Barbera, Vittorio and Guerrero, Paul and Mitra, Niloy J and Ovsjanikov, Maks},
booktitle={Computer Graphics Forum},
volume={39},
number={1},
pages={185--203},
year={2020},
organization={Wiley Online Library}
}
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. For any commercial uses or derivatives, please contact us.