Code release for the paper ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection, CVPR 2021

Authors: Jihan Yang*, Shaoshuai Shi*, Zhe Wang, Hongsheng Li, Xiaojuan Qi (*equal contribution)

[arXiv];

Our code is based on OpenPCDet v0.2. More updates on OpenPCDet are supposed to be compatible with our code.

We could not provide the above pretrained models due to Waymo Dataset License Agreement, but you should achieve similar performance by training with the default configs.

Also, the training Waymo data used in our work is version 1.0, but the version now available is version 1.2. The pretrained model on these two version data should be similar when adapted to KITTI.

We provide all pretrained models here for nuScenes > KITTI task.

We could not provide the above pretrained models due to Waymo Dataset License Agreement, but you should achieve similar performance by training with the default configs.

Please refer to INSTALL.md for the installation.

Please refer to GETTING_STARTED.md to learn more usage about this project.

• Support inference and pre-trained model

• Support training code on Waymo -> KITTI task

• Update to Latest OpenPCDet version.

• Support more adaptation tasks.

Our code is released under the Apache 2.0 license.

Our code is heavily based on OpenPCDet v0.2. Thanks OpenPCDet Development Team for their awesome codebase.

If you find this project useful in your research, please consider cite:

@inproceedings{yang2021st3d,
    title={ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection},
    author={Yang, Jihan and Shi, Shaoshuai and Wang, Zhe and Li, Hongsheng and Qi, Xiaojuan},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    year={2021}
}

@misc{openpcdet2020,
    title={OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Clouds},
    author={OpenPCDet Development Team},
    howpublished = {\url{https://github.com/open-mmlab/OpenPCDet}},
    year={2020}
}