Categorical Pose and Shape Evaluation Toolbox

CPAS Toolbox is a package for evaluation of categorical pose and shape estimation methods. It contains metrics, datasets and methods. Visit the documentation for detailed usage instructions and API reference.

Installation

pip install cpas_toolbox

Citation

If you find this library useful in your research, consider citing our conference paper or the extended journal version:

@inproceedings{bruns2023evaluation,
  title={On the evaluation of RGB-D-based categorical pose and shape estimation},
  author={Bruns, Leonard and Jensfelt, Patric},
  booktitle={Intelligent Autonomous Systems 17: Proceedings of the 17th International Conference IAS-17},
  pages={360--377},
  year={2023},
  organization={Springer}
}
@article{bruns2023rgb,
  title={RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation},
  author={Bruns, Leonard and Jensfelt, Patric},
  journal={Robotics and Autonomous Systems 168},
  year={2023}
}

Development

• Use pip install -e . to install the package in editable mode
• Use pip install -r requirements-dev.txt to install dev tools
• Use pytest -rf --cov=cpas_toolbox --cov-report term-missing tests/ to run tests and check code coverage