Self-Supervised AutoFlow

Hsin-Ping Huang, Charles Herrmann, Junhwa Hur, Erika Lu, Kyle Sargent, Austin Stone, Ming-Hsuan Yang, Deqing Sun; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 11412-11421

Abstract

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Hsin-Ping and Herrmann, Charles and Hur, Junhwa and Lu, Erika and Sargent, Kyle and Stone, Austin and Yang, Ming-Hsuan and Sun, Deqing}, title = {Self-Supervised AutoFlow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11412-11421} }