Bootstrap Your Own Correspondences

This repository will hold all the code and data for BYOC.

Bootstrap Your Own Correspondences
Mohamed El Banani and Justin Johnson

If you find this code useful, please consider citing:

@inProceedings{elbanani2021byoc,
  title={{Bootstrap Your Own Correspondences}},
  author={El Banani, Mohamed and Johnson, Justin},
  booktitle={ICCV},
  year={2021},
}

If you have any questions about the paper or the code, please feel free to email me at [email protected]

Usage Instructions

1. How to setup your environment?
2. How to download and setup the datasets?
3. How to train models?

Acknowledgments

We would like to thank the reviewers and area chairs for their valuable comments and suggestions. We also thank Richard Higgins and Karan Desai for many helpful discussions and feedback on early drafts of this work.

We would also like to acknowledge the following repositories and users for making great code openly available for us to use:

• @pytorch/pytorch
• @facebookresearch/pytorch3d for a great 3D vision library.
• @intel-isl/Open3D for easy to use implementations of traditional methods and great visualizers.