In this page, we provide download links to the datasets. Instructions on setting up and using the data is avaliable on the tutorial page.
Please send us an access request with your affiliation and role, and we will grant the access.
The complete directory tree structure of V2X-Sim 2.0 are listed below.
However, you can download any sensors of your choice
if you do not need the full dataset. For all subdirectories under
/V2X-Sim/sweeps, folders with the name id_0 contain data collected
from the roadside unit,
while folders with the name id_1 to id_5
are data collected from the vehicles.
- Preprocessed datasets & model checkpoints for coperception SDK
If you find the dataset helpful, please consider citing us.
@InProceedings{Li_2021_NeurIPS,
title = {Learning Distilled Collaboration Graph for Multi-Agent
Perception},
author = {Li, Yiming and Ren, Shunli and Wu, Pengxiang and Chen,
Siheng and Feng, Chen and Zhang, Wenjun},
booktitle = {Thirty-fifth Conference on Neural Information
Processing Systems (NeurIPS 2021)},
year = {2021}
}
@article{Li_2021_RAL,
title = {V2X-Sim: Multi-Agent Collaborative Perception Dataset and
Benchmark for Autonomous Driving},
author = {Li, Yiming and Ma, Dekun and An, Ziyan and Wang, Zixun and
Zhong, Yiqi and Chen, Siheng and Feng, Chen},
journal = {IEEE Robotics and Automation Letters},
year = {2022}
}