Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels
between two images. Despite the tremendous progress of deep learning-based optical flow …

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 …

Hierarchical concepts have proven useful in many classical and learning-based optical flow
methods regarding both accuracy and robustness. In this paper we show that such concepts …

Inaccurate optical flow estimates in and near occluded regions, and out-of-boundary regions
are two of the current significant limitations of optical flow estimation algorithms. Recent state …

Deep learning-based video denoising methods have achieved great performance
improvements in recent years. However, the expensive computational cost arising from …

The cost volume, capturing the similarity of possible correspondences across two input
images, is a key ingredient in state-of-the-art optical flow approaches. When sampling …

Optical flow seeks to estimate the per-pixel 2D motion between two frames by identifying
corresponding pixels. Current flow estimators typically involve per-pixel feature extraction …