Home

Awesome

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

Garrick Brazil, Xiaoming Liu

Introduction

Monocular 3D region proposal network source code as detailed in arXiv report, accepted to ICCV 2019 (Oral). Please also visit our project page.

Our framework is implemented and tested with Ubuntu 16.04, CUDA 8.0, Python 3, NVIDIA 1080 Ti GPU. Unless otherwise stated the below scripts and instructions assume working directory is the project root.

If you utilize this framework, please cite our ICCV 2019 paper.

@inproceedings{brazil2019m3drpn,
    title={M3D-RPN: Monocular 3D Region Proposal Network for Object Detection},
    author={Brazil, Garrick and Liu, Xiaoming},
    booktitle={Proceedings of the IEEE International Conference on Computer Vision},
    address={Seoul, South Korea},
    year={2019}
}

Setup

Training

We use visdom for visualization and graphs. Optionally, start the server by command line

python -m visdom.server -port 8100 -readonly

The port can be customized in scripts/config files. The training monitor can be viewed at http://localhost:8100

Training is split into a warmup and main configurations. Review the configurations in scripts/config for details.

// First train the warmup (without depth-aware)
python scripts/train_rpn_3d.py --config=kitti_3d_multi_warmup

// Then train the main experiment (with depth-aware)
python scripts/train_rpn_3d.py --config=kitti_3d_multi_main

If your training is accidentally stopped, you can resume at a checkpoint based on the snapshot with the restore flag. For example to resume training starting at iteration 10k, use the following command.

python scripts/train_rpn_3d.py --config=kitti_3d_multi_main --restore=10000

Testing

We provide models for the main experiments on val1 / val2 / test data splits available to download here M3D-RPN-Release.zip.

Testing requires paths to the configuration file and model weights, exposed variables near the top scripts/test_rpn_3d.py. To test a configuration and model, simply update the variables and run the test file as below.

python scripts/test_rpn_3d.py 

Contact

For questions regarding M3D-RPN, feel free to post here or directly contact the authors {brazilga, liuxm}@msu.edu.