STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation

We present a new lightweight CNN-based algorithm for multi-frame optical flow\nestimation. Our solution introduces a double recurrence over spatial scale and\ntime through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell.\nIt includes (i) a temporal recurrence based on conveying learned features\nrather than optical flow estimates; (ii) an occlusion detection process which\nis coupled with optical flow estimation and therefore uses a very limited\nnumber of extra parameters. The resulting STaRFlow algorithm gives\nstate-of-the-art performances on MPI Sintel and Kitti2015 and involves\nsignificantly less parameters than all other methods with comparable results.\n