Estimation of super-resolved video dynamics - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

Estimation of super-resolved video dynamics

Résumé

In this work, we propose an efficient methodology for video super-resolution, that is, the recovery of a sequence of high-resolution images from its low-resolution counterpart. The optimization problem associated to video super-resolution has several specificities which makes it particularly challenging. A first barrier is the high-dimensionality of the problem, which derives from the extra temporal dimension and the unknown parametrization of the dynamical model characterizing the video. A second obstacle is the non-differentiability and the non-convexity of some of the terms of the cost function: the non-differentiability stems from the use of regularization terms of the state of the art (e.g., to enforce sparsity) whereas the non-convexity appears as soon as the motion describing the video is unknown. In this paper, we propose an overall algorithmic framework to address the video super-resolution problem. Our approach is based on fast gradient evaluation methods and modern optimization techniques for non-differentiable/non-convex problems. As a consequence, unlike previous work in the field, we show that there exists a provably-convergent method estimating both the high-resolution image sequence and the underlying motion with a complexity linear in the problem dimensions. We assess the proposed optimization methods on videos of the MPI Sintel data set, known to be a challenging optical-flow benchmark.
Fichier principal
Vignette du fichier
article.pdf (5.35 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01158551 , version 1 (01-06-2015)
hal-01158551 , version 2 (18-12-2015)
hal-01158551 , version 3 (15-02-2016)

Identifiants

Citer

Patrick Héas, Angélique Drémeau, Cédric Herzet. Estimation of super-resolved video dynamics . 2015. ⟨hal-01158551v1⟩
328 Consultations
381 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More