Dictionary Learning for Deblurring and Digital Zoom

Florent Couzinie-Devy 1 Julien Mairal 2 Francis Bach 3 Jean Ponce 1
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 SIERRA - Statistical Machine Learning and Parsimony
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 : 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.
Document type :
Reports
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/inria-00627402
Contributor : Florent Couzinie-Devy <>
Submitted on : Wednesday, September 28, 2011 - 3:11:20 PM
Last modification on : Wednesday, August 7, 2019 - 12:19:23 PM
Long-term archiving on : Thursday, December 29, 2011 - 2:27:13 AM

Files

manuscript.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00627402, version 1

Collections

Citation

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

Share

Metrics

Record views

731

Files downloads

1757