This repository TreeGAN is for 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions paper accepted on ICCV 2019
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
(Dong Wook Shu, Sung Woo Park, Junseok Kwon)
TreeGAN network consists of "TreeGCN Generator" and "Discriminator".
For more details, refer our paper.
Multi Class Generation.
Single Class Generation.
Single Class Interpolation.
This FPD version is used pretrained PointNet.
This FPD version is for ShapeNet-Benchmark dataset from A Scalable Active Framework for Region Annotation in 3D Shape Collections.
We also trained our model using same dataset for evaluation.
Our pretrained PointNet-FPD version use only subset of official ShapeNet dataset to get PointNet classification performance higher than 95%.
We recommend to compose pointclouds sampled uniformly from those of ShapeNet-Benchmark dataset for training.
We evaluate FPD scores using 5000 samples obtained from fixed trained model with best performances.
FPD evaluations have to use pre_statistics file for each class or all class version.
We just provide intermediate pretrained checkpoints and generated samples having fine scores when they are trained in about 1000 epochs.
@InProceedings{Shu_2019_ICCV,
author = {Shu, Dong Wook and Park, Sung Woo and Kwon, Junseok},
title = {3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}}This project was tested on Windows 10 / Ubuntu 16.04 Using conda install command is recommended to setting.
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 _datasetpath argument.