Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
Abstract
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make such networks estimate their local uncertainty about the correctness of their prediction, which is vital information when building decisions on top of the estimations. For the first time we compare several strategies and techniques to estimate uncertainty in a large-scale computer vision task like optical flow estimation. Moreover, we introduce a new network architecture and loss function that enforce complementary hypotheses and provide uncertainty estimates efficiently with a single forward pass and without the need for sampling or ensembles. We demonstrate the quality of the uncertainty estimates, which is clearly above previous confidence measures on optical flow and allows for interactive frame rates.
Cite
Text
Ilg et al. "Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01234-2_40Markdown
[Ilg et al. "Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/ilg2018eccv-uncertainty/) doi:10.1007/978-3-030-01234-2_40BibTeX
@inproceedings{ilg2018eccv-uncertainty,
title = {{Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow}},
author = {Ilg, Eddy and Cicek, Ozgun and Galesso, Silvio and Klein, Aaron and Makansi, Osama and Hutter, Frank and Brox, Thomas},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01234-2_40},
url = {https://mlanthology.org/eccv/2018/ilg2018eccv-uncertainty/}
}