Point-GNN

This repository is the pytorch-version reimplementation of Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud, CVPR 2020. It is based on original CVPR paper and their tensorflow-version codes

Thanks owe to authors. If you find this code useful in your research, please consider citing their work:

@InProceedings{Point-GNN,
author = {Shi, Weijing and Rajkumar, Ragunathan (Raj)},
title = {Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Getting Started

Prerequisites

conda install pytorch torchvision

Install torch-scatter according to your pytorch version following instructions in this url: https://github.com/rusty1s/pytorch_scatter

To install other dependencies:

pip3 install --user opencv-python
pip3 install --user open3d-python==0.7.0.0
pip3 install --user scikit-learn
pip3 install --user tqdm
pip3 install --user shapely

KITTI Dataset

We use the KITTI 3D Object Detection dataset. Please download the dataset from the KITTI website and also download the 3DOP train/val split here. We provide extra split files for seperated classes in splits/. We recommand the following file structure:

DATASET_ROOT_DIR
├── image                    #  Left color images
│   ├── training
|   |   └── image_2            
│   └── testing
|       └── image_2 
├── velodyne                 # Velodyne point cloud files
│   ├── training
|   |   └── velodyne            
│   └── testing
|       └── velodyne 
├── calib                    # Calibration files
│   ├── training
|   |   └──calib            
│   └── testing
|       └── calib 
├── labels                   # Training labels
│   └── training
|       └── label_2
└── 3DOP_splits              # split files.
    ├── train.txt
    ├── train_car.txt
    └── ...

Download Point-GNN

Clone the repository recursively:

git clone https://github.com/Shudeng/Point-GNN.pytorch --recursive

Training

bash train.sh

License

This project is licensed under the MIT License - see the LICENSE file for details