Awesome

Point Cloud Upsampling via Disentangled Refinement

This repository contains a Tensorflow implementation of the paper:

Point Cloud Upsampling via Disentangled Refinement. <br> Ruihui Li, Xianzhi Li, Pheng-Ann Heng, Chi-Wing Fu. <br> <br> CVPR 2021

Getting Started

Clone the repository:
```
https://github.com/liruihui/Dis-PU.git
cd Dis-PU
```
Installation instructions for Ubuntu 16.04:
- Make sure <a href="https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html">CUDA</a> and <a href="https://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html">cuDNN</a> are installed. Only this configurations has been tested:
  - Python 3.6.9, TensorFlow 1.11.1
- Follow <a href="https://www.tensorflow.org/install/pip">Tensorflow installation procedure</a>.
Compile the customized TF operators by sh complile_op.sh. Follow the information from here to compile the TF operators.
Train the model: First, you need to download the training patches in HDF5 format from GoogleDrive and put it in folder data. Then run:
```
cd code
python dis-pu.py --phase train
```
Evaluate the model: First, you need to download the pretrained model from GoogleDrive, extract it and put it in folder 'model'. Then run:
```
cd code
python dis-pu.py --phase test
```
You will see the input and output results in the folder data/test/output.
The training and testing mesh files can be downloaded from GoogleDrive.

Evaluation code

We provide the evaluation code. In order to use it, you need to install the CGAL library. Please refer this link and PU-Net to install this library. Then:

cd evaluation_code
cmake .
make
./evaluation Icosahedron.off Icosahedron.xyz

The second argument is the mesh, and the third one is the predicted points.

Citation

If Dis-PU is useful for your research, please consider citing:

@inproceedings{li2021dispu,
     title={Point Cloud Upsampling via Disentangled Refinement},
     author={Li, Ruihui and Li, Xianzhi and Heng, Pheng-Ann and Fu, Chi-Wing},
     booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2021}
 }

Questions

Please contact 'lirh@cse.cuhk.edu.hk'