We learn to compute optical flow by combining a classical spatial-pyramid formulation with
deep learning. This estimates large motions in a coarse-to-fine approach by warping one …

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem.
However, the state of the art with regard to the quality of the flow has still been defined by …

Abstract FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow
estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper …

Convolutional neural networks (CNNs) have recently been very successful in a variety of
computer vision tasks, especially on those linked to recognition. Optical flow estimation has …

Recent work has shown that optical flow estimation can be formulated as a supervised
learning problem. Moreover, convolutional networks have been successfully applied to this …

Convolutional neural networks (CNNs) have recently been very successful in a variety of
computer vision tasks, especially on those linked to recognition. Optical flow estimation has …

Full-motion cost volumes play a central role in current state-of-the-art optical flow methods.
However, constructed using simple feature correlations, they lack the ability to encapsulate …

Motion analysis is one of the most fundamental and challenging problems in the field of
computer vision, which can be widely applied in many areas, such as autonomous driving …

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 …

Optical flow estimation is a crucial task in computer vision that provides low-level motion
information. Despite recent advances, real-world applications still present significant …