Skip to content
/ STSSL Public

Code for **Spatiotemporal Self-supervised Learning for Point Clouds in the Wild** (STSSL) CVPR2023

License

Notifications You must be signed in to change notification settings

YanhaoWu/STSSL

Repository files navigation

-----------------------------------------------------------------------------------

Update 19:56 8.21 2023

Code is released, modify the 'epochs' to 'stop_epoch' in trainer.stssl_trainer

-----------------------------------------------------------------------------------

**(STSSL) Spatiotemporal Self-supervised Learning for Point Clouds in the Wild **

Paper | Project page

Our project is built based on SegContrast

Installing pre-requisites:

sudo apt install build-essential python3-dev libopenblas-dev

pip3 install -r requirements.txt

pip3 install torch ninja

Installing MinkowskiEngine with CUDA support:

pip3 install -U MinkowskiEngine==0.5.4 --install-option="--blas=openblas" -v --no-deps

Data Preparation

Download KITTI inside the directory your config.dataset_path/datasets. The directory structure should be:

 ── your config.dataset_path/
    └── dataset
        └── sequences
        ├── 00/           
        │   ├── velodyne/	
        |   |	├── 000000.bin
        |   |	├── 000001.bin
        |   |	└── ...
        │   └── labels/ 
        |       ├── 000000.label
        |       ├── 000001.label
        |       └── ...
        ├── 08/ # for validation
        ├── 11/ # 11-21 for testing
        └── 21/
            └── ...

Reproducing the results

for pre-training. (We use 8 RXT3090 GPUs for pre-training)

you can just run train_stssl.py which is in tools, remember to modify the paramters of path : )

Then for fine-tuning:

you can just run train_downstream.py which is in tools, remember to adjust the learning rate: )

Of course, you can also refer to SegContrast

Any questions, touch me at [email protected]

Citation

If you use this repo, please cite as :

@inproceedings{wu2023spatiotemporal,
  title={Spatiotemporal Self-supervised Learning for Point Clouds in the Wild},
  author={Wu, Yanhao and Zhang, Tong and Ke, Wei and S{\"u}sstrunk, Sabine and Salzmann, Mathieu},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={5251--5260},
  year={2023}
}

About

Code for **Spatiotemporal Self-supervised Learning for Point Clouds in the Wild** (STSSL) CVPR2023

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages