CooPre: Cooperative Pretraining for V2X Cooperative Perception

Seth Z. Zhao, Hao Xiang, Chenfeng Xu, Xin Xia, Bolei Zhou, Jiaqi Ma

This is the official implementation of IROS 2025 paper "CooPre: Cooperative Pretraining for V2X Cooperative Perception". In this paper, we present a multi-agent self-supervised learning framwork for V2X cooperative perception, which utilizes the vast amount of unlabeled 3D V2X data to enhance the perception performance. Our study underscores the critical role of well-learned 3D representations as a promising complement to task-specific design optimizations in V2X cooperative perception.

News

• 2025/08: TurboTrain paper has been released! TurboTrain extends CooPre framework to multi-frame spatial-temporal pretraining and has been accepted to ICCV 2025.
• 2025/07: CooPre has been accepted to IROS 2025 as oral presentation.
• 2025/06: CooPre has been awarded with Best Paper Award at the CVPR 2025 DriveX Workshop.

Release Plan

• 2025/07: Full Codebase Release.
• 2025/04: Official Repo Release.

Data Download

Please check website to download the data. The data is in OPV2V format.

After downloading the data, please put the data in the following structure:

├── v2xreal
│   ├── train
|      |── 2023-03-17-15-53-02_1_0
│   ├── validate
│   ├── test

Tutorial

Environment setup

Please refer to the following steps for the environment setup:

# Create conda environment (python >= 3.7)
conda create -n coopre python=3.8
conda activate coopre
# pytorch installation
pip3 install torch torchvision torchaudio
# spconv 2.x Installation
pip install spconv-cu120
# Install other dependencies
pip install -r requirements.txt
python setup.py develop
# Install bbx nms calculation cuda version
python opencood/utils/setup.py build_ext --inplace

Running instructions

For pretraining, please run:

bash scripts/pretrain.sh

For finetuning, please run:

bash scripts/finetune.sh

For inference, please run:

bash scripts/eval.sh

Acknowledgement

CooPre belongs to the OpenCDA ecosystem family. The codebase is built upon OpenCOOD in the OpenCDA ecosystem family, and the V2X-Real, another project in OpenCDA, serves as one of the data sources for this project.

Citation

If you find this repository useful for your research, please consider giving us a star 🌟 and citing our paper.

@inproceedings{zhao2025coopre,
 title={Coopre: Cooperative pretraining for v2x cooperative perception},
 author={Zhao, Seth Z and Xiang, Hao and Xu, Chenfeng and Xia, Xin and Zhou, Bolei and Ma, Jiaqi},
 booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
 pages={11765--11772},
 year={2025},
 organization={IEEE}
}

Other useful citations:

@inproceedings{zhou2025turbotrain,
 title={TurboTrain: Towards efficient and balanced multi-task learning for multi-agent perception and prediction},
 author={Zhou, Zewei and Zhao, Seth Z and Cai, Tianhui and Huang, Zhiyu and Zhou, Bolei and Ma, Jiaqi},
 booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
 pages={4391--4402},
 year={2025}
}

@inproceedings{zhou2025v2xpnp,
 title={V2xpnp: Vehicle-to-everything spatio-temporal fusion for multi-agent perception and prediction},
 author={Zhou, Zewei and Xiang, Hao and Zheng, Zhaoliang and Zhao, Seth Z and Lei, Mingyue and Zhang, Yun and Cai, Tianhui and Liu, Xinyi and Liu, Johnson and Bajji, Maheswari and others},
 booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
 pages={25399--25409},
 year={2025}
}

@inproceedings{xiang2024v2x,
 title={V2x-real: a largs-scale dataset for vehicle-to-everything cooperative perception},
 author={Xiang, Hao and Zheng, Zhaoliang and Xia, Xin and Xu, Runsheng and Gao, Letian and Zhou, Zewei and Han, Xu and Ji, Xinkai and Li, Mingxi and Meng, Zonglin and others},
 booktitle={European Conference on Computer Vision},
 pages={455--470},
 year={2024},
 organization={Springer}
}