Occlusion Aware Unsupervised Learning of Optical Flow
This work improves unsupervised optical flow estimation for computer vision applications, though it is incremental as it builds on existing unsupervised methods.
The paper tackles the problem of optical flow estimation by addressing occlusion and large motion limitations in unsupervised learning, achieving results where the unsupervised method outperforms supervised learning on the KITTI dataset.
It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we introduce a new method which models occlusion explicitly and a new warping way that facilitates the learning of large motion. Our method shows promising results on Flying Chairs, MPI-Sintel and KITTI benchmark datasets. Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.