--- license: bsd-3-clause language: - en tags: - scene-flow - point-cloud - codebase - 3d-vision ---

opensceneflow

๐Ÿ’ž If you find [*OpenSceneFlow*](https://github.com/KTH-RPL/OpenSceneFlow) useful to your research, please cite [**our works** ๐Ÿ“–](#cite-us) and give [a star ๐ŸŒŸ](https://github.com/KTH-RPL/OpenSceneFlow) as encouragement. (เฉญหŠ๊’ณโ€‹ห‹)เฉญโœง [*OpenSceneFlow*](https://github.com/KTH-RPL/OpenSceneFlow) is a codebase for point cloud scene flow estimation. Please check the usage on [KTH-RPL/OpenSceneFlow](https://github.com/KTH-RPL/OpenSceneFlow). Here we upload our demo data and checkpoint for the community. ## ๐ŸŽ One repository, All methods! You can try following methods in [our OpenSceneFlow](https://github.com/KTH-RPL/OpenSceneFlow) without any effort to make your own benchmark. Officially: - [x] [HiMo (SeFlow++)](https://arxiv.org/abs/2503.00803): T-RO 2025 - [x] [VoteFlow](https://arxiv.org/abs/2503.22328): CVPR 2025 - [x] [SSF](https://arxiv.org/abs/2501.17821) (Ours ๐Ÿš€): ICRA 2025 - [x] [Flow4D](https://ieeexplore.ieee.org/document/10887254): RA-L 2025 - [x] [SeFlow](https://arxiv.org/abs/2407.01702) (Ours ๐Ÿš€): ECCV 2024 - [x] [DeFlow](https://arxiv.org/abs/2401.16122) (Ours ๐Ÿš€): ICRA 2024
Reoriginse to our codebase: - [x] [FastFlow3d](https://arxiv.org/abs/2103.01306): RA-L 2021 - [x] [ZeroFlow](https://arxiv.org/abs/2305.10424): ICLR 2024, their pre-trained weight can covert into our format easily through [the script](https://github.com/KTH-RPL/OpenSceneFlow/tools/zerof2ours.py). - [x] [NSFP](https://arxiv.org/abs/2111.01253): NeurIPS 2021, faster 3x than original version because of [our CUDA speed up](https://github.com/KTH-RPL/OpenSceneFlow/assets/cuda/README.md), same (slightly better) performance. Done coding, public after review. - [x] [FastNSF](https://arxiv.org/abs/2304.09121): ICCV 2023. Done coding, public after review. - [ ] ... more on the way
## Notes The tree of uploaded files: * [ModelName_best].ckpt: means the model evaluated in the public leaderboard page provided by authors or our retrained with the best parameters. * [demo-data-v2.zip](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/demo_data.zip): 1.2GB, a mini-dataset for user to quickly run train/val code. Check usage in [this section](https://github.com/KTH-RPL/SeFlow?tab=readme-ov-file#1-run--train). * [waymo_map.tar.gz](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/waymo_map.tar.gz): to successfully process waymo data with ground segmentation included to unified h5 file. Check usage in [this README](https://github.com/KTH-RPL/SeFlow/blob/main/dataprocess/README.md#waymo-dataset). * [demo_data.zip](https://huggingface.co/kin-zhang/OpenSceneFlow/blob/main/demo_data.zip): 1st version (will deprecated later) 613Mb, a mini-dataset for user to quickly run train/val code. Check usage in [this section](https://github.com/KTH-RPL/OpenSceneFlow?tab=readme-ov-file#1-run--train). All test result reports can be found [v2 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/6) and [v1 leaderboard](https://github.com/KTH-RPL/DeFlow/discussions/2). ## Cite Us *OpenSceneFlow* is designed by [Qingwen Zhang](https://kin-zhang.github.io/) from DeFlow and SeFlow project. If you find it useful, please cite our works: ```bibtex @inproceedings{zhang2024seflow, author={Zhang, Qingwen and Yang, Yi and Li, Peizheng and Andersson, Olov and Jensfelt, Patric}, title={{SeFlow}: A Self-Supervised Scene Flow Method in Autonomous Driving}, booktitle={European Conference on Computer Vision (ECCV)}, year={2024}, pages={353โ€“369}, organization={Springer}, doi={10.1007/978-3-031-73232-4_20}, } @inproceedings{zhang2024deflow, author={Zhang, Qingwen and Yang, Yi and Fang, Heng and Geng, Ruoyu and Jensfelt, Patric}, booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)}, title={{DeFlow}: Decoder of Scene Flow Network in Autonomous Driving}, year={2024}, pages={2105-2111}, doi={10.1109/ICRA57147.2024.10610278} } @article{zhang2025himo, title={HiMo: High-Speed Objects Motion Compensation in Point Clouds}, author={Zhang, Qingwen and Khoche, Ajinkya and Yang, Yi and Ling, Li and Sina, Sharif Mansouri and Andersson, Olov and Jensfelt, Patric}, year={2025}, journal={arXiv preprint arXiv:2503.00803}, } ``` And our excellent collaborators works as followings: ```bibtex @inproceedings{lin2025voteflow, title={VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow}, author={Lin, Yancong and Wang, Shiming and Nan, Liangliang and Kooij, Julian and Caesar, Holger}, booktitle={CVPR}, year={2025}, } @article{kim2025flow4d, author={Kim, Jaeyeul and Woo, Jungwan and Shin, Ukcheol and Oh, Jean and Im, Sunghoon}, journal={IEEE Robotics and Automation Letters}, title={Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation}, year={2025}, volume={10}, number={4}, pages={3462-3469}, doi={10.1109/LRA.2025.3542327} } @article{khoche2025ssf, title={SSF: Sparse Long-Range Scene Flow for Autonomous Driving}, author={Khoche, Ajinkya and Zhang, Qingwen and Sanchez, Laura Pereira and Asefaw, Aron and Mansouri, Sina Sharif and Jensfelt, Patric}, journal={arXiv preprint arXiv:2501.17821}, year={2025} } ``` Feel free to contribute your method and add your bibtex here by pull request!