Home

Awesome

<!-- ## FSD: Fully Sparse 3D Object Detection & SST: Single-stride Sparse Transformer --> <!-- [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/embracing-single-stride-3d-object-detector/3d-object-detection-on-waymo-pedestrian)](https://paperswithcode.com/sota/3d-object-detection-on-waymo-pedestrian?p=embracing-single-stride-3d-object-detector) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/embracing-single-stride-3d-object-detector/3d-object-detection-on-waymo-cyclist)](https://paperswithcode.com/sota/3d-object-detection-on-waymo-cyclist?p=embracing-single-stride-3d-object-detector) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/embracing-single-stride-3d-object-detector/3d-object-detection-on-waymo-vehicle)](https://paperswithcode.com/sota/3d-object-detection-on-waymo-vehicle?p=embracing-single-stride-3d-object-detector) -->

🔥 We release the code of CTRL, the first open-sourced LiDAR-based auto-labeling system. See ctrl_instruction.

🔥 We release FSDv2. Better performance, easier use! Support Waymo, nuScenes, and Argoverse 2. See fsdv2_instruction.


This repo contains official implementations of our series of work in LiDAR-based 3D object detection:

Users could follow the instructions in docs to use this repo.

NEWS

<!-- **Visualization of a SST detection sequence by AB3DMOT tracking:** ![demo-min](https://user-images.githubusercontent.com/21312704/145702575-24647aed-256d-486c-835f-730584cf99ee.gif) -->

Citation

Please consider citing our work as follows if it is helpful.

Since FSD++ (TPAMI version) is accidentally excluded in Google Scholar search results, if possible, please kindly use the following bibtex.

@inproceedings{fan2022embracing,
  title={{Embracing Single Stride 3D Object Detector with Sparse Transformer}},
  author={Fan, Lue and Pang, Ziqi and Zhang, Tianyuan and Wang, Yu-Xiong and Zhao, Hang and Wang, Feng and Wang, Naiyan and Zhang, Zhaoxiang},
  booktitle={CVPR},
  year={2022}
}
@inproceedings{fan2022fully,
  title={{Fully Sparse 3D Object Detection}},
  author={Fan, Lue and Wang, Feng and Wang, Naiyan and Zhang, Zhaoxiang},
  booktitle={NeurIPS},
  year={2022}
}
@article{fan2023super,
  title={Super Sparse 3D Object Detection},
  author={Fan, Lue and Yang, Yuxue and Wang, Feng and Wang, Naiyan and Zhang, Zhaoxiang},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2023}
}
@inproceedings{fan2023once,
  title={Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection},
  author={Fan, Lue and Yang, Yuxue and Mao, Yiming and Wang, Feng and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang},
  booktitle={ICCV},
  year={2023}
}
@article{fan2023fsdv2,
  title={FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels},
  author={Fan, Lue and Wang, Feng and Wang, Naiyan and Zhang, Zhaoxiang},
  journal={arXiv preprint arXiv:2308.03755},
  year={2023}
}

Acknowledgments

This project is based on the following codebases.

Thank the authors of CenterPoint for providing their detailed results.