Home

Awesome

Equi-Articulated-Pose

Code repository for our paper Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance.

overall_pipeline

Links

Environment and package dependency

Create a virtual environment:

conda env create -f env.yaml

Install the vgtk package:

cd vgtk && python setup.py install && cd ..

Data

Please download data from this link and put them under the folder ./data.

Training

bash scripts/train/${CATEGORY_NAME}.sh

Evaluation

bash scripts/val/${CATEGORY_NAME}.sh

Checkpoints

Please download trained models from this link and put them under the folder ./ckpt.

Contact

Feel free to contact me at xymeow7@gmail.com or create a Github issue if you have any question regarding the repository. Thanks for your interest.

Citation

If you find the code useful for your research, please cite our paper.

@inproceedings{liu2023self,
  title={Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE (3) Equivariance},
  author={Liu, Xueyi and Zhang, Ji and Hu, Ruizhen and Huang, Haibin and Wang, He and Yi, Li},
  booktitle={The Eleventh International Conference on Learning Representations},
  year={2023}
}

License

The majority of the code is licensed under an Apache License 2.0 (see LICENSE file for details).

Reference

Part of the code is taken from EPN, equi-pose. Thank you to the authors of these projects for their great work.