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

Pierre Godet    Alexandre Boulch    Aurelien Plyer    Guy Le Besnerais  

ICPR 2020

Paper   Code   

project teaser

Abstract

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.

BibTeX

@inproceedings{godet2021starflow,
  title={STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation},
  author={Godet, Pierre and Boulch, Alexandre and Plyer, Aur{\'e}lien and Le Besnerais, Guy},
  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
  pages={2462--2469},
  year={2021},
  organization={IEEE}
}