Optical Flow Estimation is the problem of finding pixel-wise motions between consecutive images.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.
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.
Ranked #4 on Video Frame Interpolation on UCF101
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.
Optical flow estimation has not been among the tasks where CNNs were successful.
RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes.
Ranked #2 on Optical Flow Estimation on Sintel-final
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account.