Multi-View Partial Point Clouds for Completion and Registration

MVP Benchmark

MVP Benchmark for Multi-View Partial Point Cloud Completion and Registration

Overview

This repository introduces the MVP Benchmark for partial point cloud COMPLETION and REGISTRATION, and it also includes following recent methods:

Completetion: [1] PCN; [2] ECG; [3] VRCNet
Registration: [1] DCP; [2] DeepGMR; [3] IDAM

This repository is implemented in Python 3.7, PyTorch 1.5.0, CUDA 10.1 and gcc > 5.

Installation

Install Anaconda, and then use the following command:

git clone --depth=1 https://github.com/paul007pl/MVP_Benchmark.git
cd MVP_Benchmark; source setup.sh;

If your connection to conda and pip is unstable, it is recommended to manually follow the setup steps in setup.sh.

MVP Dataset

Download corresponding dataset:

Completion : Google Drive or 百度网盘 (code: p364)
Registration : Google Drive or 百度网盘 (code: p364)

Usage

For both completion and registration:

cd completion or cd registration
To train a model: run python train.py -c ./cfgs/*.yaml, e.g. python train.py -c ./cfgs/pcn.yaml
To test a model: run python test.py -c ./cfgs/*.yaml, e.g. python test.py -c ./cfgs/pcn.yaml
Config for each algorithm can be found in cfgs/.
run_train.sh and run_test.sh are provided for SLURM users.
Different partial point clouds for the same CAD Model:

High-quality complete point clouds:

[Citation]

If you find our code useful, please cite our paper:

@article{pan2021variational,
  title={Variational Relational Point Completion Network},
  author={Pan, Liang and Chen, Xinyi and Cai, Zhongang and Zhang, Junzhe and Zhao, Haiyu and Yi, Shuai and Liu, Ziwei},
  journal={arXiv preprint arXiv:2104.10154},
  year={2021}
}