Many classical and learning-based optical flow methods rely on hierarchical concepts to
improve both accuracy and robustness. However, one of the currently most successful …

To date, top-performing optical flow estimation methods only take pairs of consecutive
frames into account. While elegant and appealing, the idea of using more than two frames …

The difficulty of annotating training data is a major obstacle to using CNNs for low-level tasks
in video. Synthetic data often does not generalize to real videos, while unsupervised …

Learning matching costs has been shown to be critical to the success of the state-of-the-art
deep stereo matching methods, in which 3D convolutions are applied on a 4D feature …

There is a growing consensus in computer vision that symmetric optical flow estimation
constitutes a better model than a generic asymmetric one for its independence of the …

Optical flow estimation is a challenging task consisting of predicting per-pixel motion vectors
between images. Recent methods have employed larger and more complex models to …

Although CNN-based optical flow methods have achieved remarkable performance in terms
of computational accuracy and efficiency, the issue of edge-blurring caused by large …

Optical flow estimation a process of predicting pixel-wise displacement between consecutive
frames has commonly been approached as a regression task in the age of deep learning …

We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation.
Our solution introduces a double recurrence over spatial scale and time through repeated …

Attention-based motion aggregation concepts have recently shown their usefulness in
optical flow estimation, in particular when it comes to handling occluded regions. However …