STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

Alexandre Boulch

Résumé

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.
Fichier principal
Vignette du fichier
Dtis20191 pre print.pdf (2.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03132982 , version 1 (05-02-2021)

Identifiants

  • HAL Id : hal-03132982 , version 1

Citer

Pierre Godet, Alexandre Boulch, Aurélien Plyer, Guy Le Besnerais. STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation. ICPR 2020, Jan 2021, Milan (virtuel), Italy. ⟨hal-03132982⟩
54 Consultations
41 Téléchargements

Partager

Gmail Facebook X LinkedIn More