Skip to content

Latest commit

 

History

History
71 lines (55 loc) · 2.45 KB

README.md

File metadata and controls

71 lines (55 loc) · 2.45 KB

MonoGRNet: A Geometric Reasoning Network for 3D Object Localization

Watch the video

Created by Zengyi Qin, Jinglu Wang and Yan Lu. The repository contains an implementation of this AAAI Oral Paper.


Related Project

Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

Please cite this paper if you find the repository helpful:

@article{qin2019monogrnet, 
  title={MonoGRNet: A Geometric Reasoning Network for 3D Object Localization}, 
  author={Zengyi Qin and Jinglu Wang and Yan Lu},
  journal={The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)},
  year={2019}
}

Prerequisites

  • Ubuntu 16.04
  • Python 2.7
  • Tensorflow 1.4.0

Install

Clone this repository

git clone https://github.com/Zengyi-Qin/MonoGRNet.git

Download the Kitti Object Detection Dataset (image, calib and label) and place it into data/KittiBox. The folder should be in the following structure:

data
    KittiBox
        training
            calib
            image_2
            label_2
        train.txt
        val.txt

The train-val split train.txt and val.txt are contained in this repository.

Compile the Cython module:

python compile_cython.py

Download the pretrained model from this link and extract.

Training and evaluation

Run the training script and specify the GPU to use:

python train.py --gpus 0

The evaluation is done during training. You can adjust the evaluation intervals in hypes/kittiBox.json.

Visualization

cd visualize && mkdir visualize
python visualize.py

Acknowledgement

We would like to thank the authors of KittiBox for their code.