|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
#2 best model for Skeleton Based Action Recognition on JHMDB Pose Tracking
Optical flow estimation has not been among the tasks where CNNs were successful.
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account.
We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training.
It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow.
#2 best model for Dense Pixel Correspondence Estimation on HPatches
Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.
#3 best model for Video Frame Interpolation on Middlebury
Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content and dynamics.