Dictionary Learning for Deblurring and Digital Zoom - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Technical Report) International Journal of Computer Vision Year : 2011

Dictionary Learning for Deblurring and Digital Zoom


This paper proposes a novel approach to image deblurring and digital zooming using sparse local models of image appearance. These models, where small image patches are represented as linear combinations of a few elements drawn from some large set (dictionary) of candidates, have proven well adapted to several image restoration tasks. A key to their success has been to learn dictionaries adapted to the reconstruction of small image patches. In contrast, recent works have proposed instead to learn dictionaries which are not only adapted to data reconstruction, but also tuned for a specific task. We introduce here such an approach to deblurring and digital zoom, using pairs of blurry/sharp (or low-/high-resolution) images for training, as well as an effective stochastic gradient algorithm for solving the corresponding optimization task. Although this learning problem is not convex, once the dictionaries have been learned, the sharp/high-resolution image can be recovered via convex optimization at test time. Experiments with synthetic and real data demonstrate the effectiveness of the proposed approach, leading to state-of-the-art performance for non-blind image deblurring and digital zoom.
Fichier principal
Vignette du fichier
manuscript.pdf (553.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00627402 , version 1 (28-09-2011)


  • HAL Id : inria-00627402 , version 1


Florent Couzinie-Devy, Julien Mairal, Francis Bach, Jean Ponce. Dictionary Learning for Deblurring and Digital Zoom. [Technical Report] 2011. ⟨inria-00627402⟩
529 View
1050 Download


Gmail Facebook X LinkedIn More