STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation
This work addresses efficient optical flow estimation for computer vision applications, offering a novel lightweight method that reduces computational costs while maintaining high accuracy.
The authors tackled multi-frame optical flow estimation by introducing a lightweight CNN-based algorithm with a spatiotemporal recurrent cell, achieving state-of-the-art performance on MPI Sintel and Kitti2015 benchmarks with significantly fewer parameters.
We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results.