Non-local sparse models for image restoration

Abstract

We propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. On the other hand, explicitly exploiting the self-similarities of natural images has led to the successful non-local means approach to image restoration. We propose simultaneous sparse coding as a framework for combining these two approaches in a natural manner. This is achieved by jointly decomposing groups of similar signals on subsets of the learned dictionary. Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost.

DOI: 10.1109/ICCV.2009.5459452
View Slides

Extracted Key Phrases

0501001502008200920102011201220132014201520162017
Citations per Year

984 Citations

Semantic Scholar estimates that this publication has 984 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Mairal2009NonlocalSM, title={Non-local sparse models for image restoration}, author={Julien Mairal and Francis R. Bach and Jean Ponce and Guillermo Sapiro and Andrew Zisserman}, journal={2009 IEEE 12th International Conference on Computer Vision}, year={2009}, pages={2272-2279} }