This repository holds all the code and data for the paper:
Self-supervised Correspondence Estimation via Multiview Registration
Mohamed El Banani, Ignacio Rocco, David Novotny, Andrea Vedaldi,
Natalia Neverova, Justin Johnson, Benjamin Graham
If you find this code useful, please consider citing:
@inProceedings{elbanani2023syncmatch,
title={{Self-supervised Correspondence Estimation via Multiview Registration}},
author={El Banani, Mohamed and Rocco, Ignacio and Novotny, David and Vedaldi, Andrea and Neverova, Natalia and Johnson, Justin and Graham, Benjamin}
booktitle={WACV},
year={2023},
}
If you have any questions, please feel free to email me at [email protected].
- How to setup your environment?
- How to download and setup the datasets?
- How to train model and ablations in paper?
- How to run the evaluation?
See the CONTRIBUTING file for how to help out.
SyncMatch is CC-BY-NC licensed, as found in the LICENSE file.
We would like to thank Karan Desai, Richard Higgins, David Fouhey, Daniel Geng, and Dandan Shan for feedback on early drafts of this work.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent