Index repo for the PACE project. It consists of two parts: 1) ROBIN, which is a framework for rejecting outliers using compatibility graphs, and 2) PACE, which consists of solvers for solving category-level object registration problems.
ROBIN can be found here.
PACE solvers will be released as soon as possible.
If you find our work helpful, consider citing:
@article{Shi22arxiv-PACE,
author = {J. Shi and H. Yang and L. Carlone},
title = {Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from {2D and 3D} Semantic Keypoints},
journal = {arXiv preprint: 2206.12498},
pdf = {https://arxiv.org/pdf/2206.12498.pdf},
Year = {2022}
}
@InProceedings{Shi21rss-pace,
title={Optimal Pose and Shape Estimation for Category-level {3D} Object Perception},
author={J. Shi and H. Yang and L. Carlone},
booktitle={Robotics: Science and Systems (RSS)},
note = {arXiv preprint: 2104.08383},
pdf={https://arxiv.org/pdf/2104.08383.pdf},
year={2021},
}
@InProceedings{Shi21icra-robin,
title={{ROBIN:} a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants},
author={J. Shi and H. Yang and L. Carlone},
booktitle={IEEE Intl. Conf. on Robotics and Automation (ICRA)},
note = {arXiv preprint: 2011.03659},
pdf={https://arxiv.org/pdf/2011.03659.pdf},
year={2021}
}