This repository PC-cGAN is for Conditional GAN for Point Cloud Generation paper accepted on ACCV 2022

PC-cGAN network consists of "Pre-Generator", "Conditional Modifier", and "Discriminator with a Classifier".

For more details, refer our paper.

This project was tested on Ubuntu 18.04 Using conda install command is recommended to setting.

• Python 3.6
• Numpy
• Pytorch 1.9
• visdom
• scipy 1.5
• tqdm

In our project, arguments.py file has almost every parameters to specify for training.

For example, if you want to train, it needs to specify dataset_path argument.