Computer Science – Learning
Scientific paper
2011-10-05
Computer Science
Learning
Scientific paper
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.
Bach Francis
Couzinie-Devy Florent
Mairal Julien
Ponce Jean
No associations
LandOfFree
Dictionary Learning for Deblurring and Digital Zoom does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Dictionary Learning for Deblurring and Digital Zoom, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dictionary Learning for Deblurring and Digital Zoom will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-325096