This is our implementation of Meta-PCD which is a meta-network-based method for point cloud denoising.
CUDA and CuDNN (changing the code to run on CPU should require few changes)
Python 2.7
PyTorch 1.0
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
git clone https://github.com/xtwang2020/Meta-PCD.git
To denoise point clouds using default settings and calculate the metric:
cd Meta-PCD python test.py python metric_cal.py
Part of this implementation is based on PointCleanNet and PCPNet.