|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.
Finally, the two input images are warped and linearly fused to form each intermediate frame.
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.
#4 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.