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 …

In estimating optical flow using convolutional neural networks, a gap in accuracy exists
between supervised and unsupervised training because supervised methods can obtain …

Learning-based optical flow estimation has been dominated with the pipeline of cost volume
with convolutions for flow regression, which is inherently limited to local correlations and …

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 …

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 study the unsupervised learning of CNNs for optical flow estimation using proxy ground
truth data. Supervised CNNs, due to their immense learning capacity, have shown superior …

We propose a novel data augmentation approach, DistractFlow, for training optical flow
estimation models by introducing realistic distractions to the input frames. Based on a mixing …

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 …

We investigate two crucial and closely-related aspects of CNNs for optical flow estimation:
models and training. First, we design a compact but effective CNN model, called PWC-Net …

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 …