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.
@article{arxiv.2212.01762,
title = {Self-supervised AutoFlow},
author = {Hsin-Ping Huang and Charles Herrmann and Junhwa Hur and Erika Lu and Kyle Sargent and Austin Stone and Ming-Hsuan Yang and Deqing Sun},
journal= {arXiv preprint arXiv:2212.01762},
year = {2023}
}