Learning a convolutional neural network for non-uniform motion blur removal

Jian Sun 1 Wenfei Cao 1 Zongben Xu 1 Jean Ponce 2, 3
3 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image. We propose a deep learning approach to predicting the probabilistic distribution of motion blur at the patch level using a convolutional neural network (CNN). We further extend the candidate set of motion kernels predicted by the CNN using carefully designed image rotations. A Markov random field model is then used to infer a dense non-uniform motion blur field enforcing motion smoothness. Finally, motion blur is removed by a non-uniform de-blurring model using patch-level image prior. Experimental evaluations show that our approach can effectively estimate and remove complex non-uniform motion blur that is not handled well by previous approaches.
Type de document :
Communication dans un congrès
CVPR 2015 - IEEE Conference on Computer Vision and Pattern Recognition 2015, Jun 2015, Boston, United States. IEEE, 2015, 〈10.1109/CVPR.2015.7298677〉
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01250478
Contributeur : Minsu Cho <>
Soumis le : lundi 4 janvier 2016 - 19:15:45
Dernière modification le : mardi 17 avril 2018 - 11:31:20
Document(s) archivé(s) le : vendredi 15 avril 2016 - 16:21:28

Fichier

sun2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce. Learning a convolutional neural network for non-uniform motion blur removal. CVPR 2015 - IEEE Conference on Computer Vision and Pattern Recognition 2015, Jun 2015, Boston, United States. IEEE, 2015, 〈10.1109/CVPR.2015.7298677〉. 〈hal-01250478〉

Partager

Métriques

Consultations de la notice

182

Téléchargements de fichiers

182