STFlow: Self-Taught Optical Flow Estimation Using Pseudo Labels
Lists
Only you see this
Abstract
The Deep learning of optical flow has been an active area for its empirical success. For the difficulty of obtaining accurate dense correspondence labels, unsupervised learning of optical flow has drawn more and more attention, while the accuracy is still far from satisfaction. By holding the philosophy that better estimation models can be trained with better-approximated labels, which in turn can be obtained from better estimation models, we propose a self-taught learning framework to continually improve the accuracy using self-generated pseudo labels. The estimated optical flow is first filtered by bidirectional flow consistency validation and occlusion-aware dense labels are then generated by edge-aware interpolation from selected sparse matches. Moreover, by combining reconstruction loss with regression loss on the generated pseudo labels, the performance is further improved. The experimental results demonstrate that our models achieve state-of-the-art results among unsupervised methods on the public KITTI, MPI-Sintel and Flying Chairs datasets.
BibTeX
@article{ren2020stflow,
author = {Zhe Ren and Wenhan Luo and Junchi Yan and Wenlong Liao and Xiaokang Yang and Alan L. Yuille and Hongyuan Zha},
title = {{STFlow: Self-Taught Optical Flow Estimation Using Pseudo Labels}},
journal = {IEEE Trans. Image Process.},
year = {2020},
doi = {10.1109/tip.2020.3024015},
}Loading related content...