This repository contains the source code for the paper PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths. The project page is here.
@inproceedings{wen2021pmp,
title={PMP-Net: Point cloud completion by learning multi-step point moving paths},
author={Wen, Xin and Xiang, Peng and Han, Zhizhong and Cao, Yan-Pei and Wan, Pengfei and Zheng, Wen and Liu, Yu-Shen},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2021}
}
We use the PCN and Compeletion3D datasets in our experiments, which are available below:
The pretrained models on Completion3D and PCN dataset are available as follows:
Backup Links:
- PMP-Net_pre-trained (pwd: n7t4)
cd PMP-Net
pip install -r requirements.txt
NOTE: PyTorch >= 1.4 of cuda version are required.
cd pointnet2_ops_lib
python setup.py install
cd ..
cd Chamfer3D
python setup.py install
You need to update the file path of the datasets:
__C.DATASETS.COMPLETION3D.PARTIAL_POINTS_PATH = '/path/to/datasets/Completion3D/%s/partial/%s/%s.h5'
__C.DATASETS.COMPLETION3D.COMPLETE_POINTS_PATH = '/path/to/datasets/Completion3D/%s/gt/%s/%s.h5'
__C.DATASETS.SHAPENET.PARTIAL_POINTS_PATH = '/path/to/datasets/ShapeNet/ShapeNetCompletion/%s/partial/%s/%s/%02d.pcd'
__C.DATASETS.SHAPENET.COMPLETE_POINTS_PATH = '/path/to/datasets/ShapeNet/ShapeNetCompletion/%s/complete/%s/%s.pcd'
# Dataset Options: Completion3D, Completion3DPCCT, ShapeNet, ShapeNetCars
__C.DATASET.TRAIN_DATASET = 'ShapeNet'
__C.DATASET.TEST_DATASET = 'ShapeNet'
To train PMP-Net, you can simply use the following command:
python main_*.py # remember to change '*' to 'c3d' or 'pcn'
To test or inference, you should specify the path of checkpoint if the config_*.py file
__C.CONST.WEIGHTS = "path to your checkpoint"
then use the following command:
python main_*.py --test
python main_*.py --inference
Some of the code of this repo is borrowed from GRNet and pytorchpointnet++. We thank the authors for their great job!
This project is open sourced under MIT license.