CoSense3D

This Repo provides all datasets or their external links for the project CoSense3D.
The related datasets are:

- [__COMAP__](https://data.uni-hannover.de/vault/ikg/yuan/cosense3d/COMAP/): A synthetic data generated by CARLA for cooperative perception.

- [__OPV2Vt__](https://data.uni-hannover.de/vault/ikg/yuan/cosense3d/OPV2Vt/): A synthetic data generated by CARLA with the replay files provided by the dataset [OPV2V](https://mobility-lab.seas.ucla.edu/opv2v/) for the purpose of globally time-aligned cooperative object detection (TA-COOD). The original replay files are interpolated to obtain the object and sensor locations at sub-frames. Each frame is spitted into 10 sub-frames for simulation.

- [__DairV2Xt__](https://data.uni-hannover.de/vault/ikg/yuan/cosense3d/DairV2Xt/): New generate meta files based on dataset [DAIR-V2X](https://thudair.baai.ac.cn/index) for the project CoSense3D with localization correction and ground truth generate for TA-COOD.

- [__OPV2Va__](https://data.uni-hannover.de/vault/ikg/yuan/cosense3d/OPV2Va/): A synthetic data generated by CARLA with the replay files provided by the dataset [OPV2V](https://mobility-lab.seas.ucla.edu/opv2v/) augmented with semantic labels.

> [__!NOTE__]
> If you find the downloading speed is very slow, you can also try the Baidu Cloud: 链接: https://pan.baidu.com/s/12HZ1yk0y84NJfStZADMstA?pwd=hkja 提取码: hkja
--来自百度网盘超级会员v1的分享