Jiaru Zhong, Jiahao Wang, Jiahui Xu, Xiaofan Li, Zaiqing Nie*, Haibao Yu*
August 31, 2025: The code and model have been open-sourced.July 25, 2025: CoopTrack is available at arXiv now. And CoopTrack is selected as Highlight.June 26, 2025: CoopTrack has been accepted by ICCV 2025! We will release our paper and code soon!
Cooperative perception aims to address the inherent limitations of single-vehicle autonomous driving systems through information exchange among multiple agents. Previous research has primarily focused on single-frame perception tasks. However, the more challenging cooperative sequential perception tasks, such as cooperative 3D multi-object tracking, have not been thoroughly investigated. Therefore, we propose CoopTrack, a fully instance-level end-to-end framework for cooperative tracking, featuring learnable instance association, which fundamentally differs from existing approaches. CoopTrack transmits sparse instance-level features that significantly enhance perception capabilities while maintaining low transmission costs. Furthermore, the framework comprises two key components: Multi-Dimensional Feature Extraction, and Cross-Agent Association and Aggregation, which collectively enable comprehensive instance representation with semantic and motion features, and adaptive cross-agent association and fusion based on a feature graph. Experiments on both the V2X-Seq and Griffin datasets demonstrate that CoopTrack achieves excellent performance. Specifically, it attains state-of-the-art results on V2X-Seq, with 39.0% mAP and 32.8% AMOTA.
If you have any questions, please contact Jiaru Zhong via email (zhong.jiaru@outlook.com).
If you find CoopTrack is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.
@article{zhong2025cooptrack,
title={CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception},
author={Zhong, Jiaru and Wang, Jiahao and Xu, Jiahui and Li, Xiaofan and Nie, Zaiqing and Yu, Haibao},
journal={arXiv preprint arXiv:2507.19239},
year={2025}
}
We are deeply grateful for the following outstanding opensource work; without them, our work would not have been possible.