Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

Résumé

Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods. Since physics is too restrictive for describing the full visual content of generic videos, we introduce PhyDNet, a two-branch deep architecture , which explicitly disentangles PDE dynamics from unknown complementary information. A second contribution is to propose a new recurrent physical cell (PhyCell), inspired from data assimilation techniques, for performing PDE-constrained prediction in latent space. Extensive experiments conducted on four various datasets show the ability of PhyDNet to outperform state-of-the-art methods. Ab-lation studies also highlight the important gain brought out by both disentanglement and PDE-constrained prediction. Finally, we show that PhyDNet presents interesting features for dealing with missing data and long-term forecasting.
Fichier principal
Vignette du fichier
Phydnet_paper.pdf (9.05 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02947331 , version 1 (23-09-2020)

Identifiants

Citer

Vincent Le Guen, Nicolas Thome. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction. Computer Vision and Pattern Recognition 2020 (CVPR), Jun 2020, Seattle, United States. ⟨10.1109/CVPR42600.2020.01149⟩. ⟨hal-02947331⟩
96 Consultations
32 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More