What Matters in Unsupervised Optical Flow
Abstract
We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.
Cite
Text
Jonschkowski et al. "What Matters in Unsupervised Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58536-5_33Markdown
[Jonschkowski et al. "What Matters in Unsupervised Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/jonschkowski2020eccv-matters/) doi:10.1007/978-3-030-58536-5_33BibTeX
@inproceedings{jonschkowski2020eccv-matters,
title = {{What Matters in Unsupervised Optical Flow}},
author = {Jonschkowski, Rico and Stone, Austin and Barron, Jonathan T. and Gordon, Ariel and Konolige, Kurt and Angelova, Anelia},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58536-5_33},
url = {https://mlanthology.org/eccv/2020/jonschkowski2020eccv-matters/}
}