We propose a differentiable algorithm for image restoration inspired by the success of sparse models and self-similarity priors for natural images. Our approach builds upon the concept of joint sparsity between groups of similar image patches, and we show how this simple idea can be implemented in a differentiable architecture, allowing end-to-end training. The algorithm has the advantage of being interpretable, performing sparse decompositions of image patches, while being more parameter efficient than recent deep learning methods. We evaluate our algorithm on grayscale and color denoising, where we achieve competitive results, and on demoisaicking, where we outperform the most recent state-of-the-art deep learning model with 47 times less...
Sparse representation models code an image patch as a linear combination of a few atoms chosen out f...
Traditional patch-based sparse representation modeling of natural images usually suffer from two pro...
Abstract In image processing, sparse coding has been known to be relevant to both variational and Ba...
The COVID-19 pandemic has imposed to transform the face-to-face version of ECCV 2020 into an online ...
The COVID-19 pandemic has imposed to transform the face-to-face version of ECCV 2020 into an online ...
Group-based sparse representation (GSR) uses image nonlocal self-similarity (NSS) prior to grouping ...
Abstract—As a powerful statistical image modeling technique, sparse representation has been successf...
Patch based image modeling has achieved a great suc-cess in low level vision such as image denoising...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Image prior models based on sparse and redundant representations are attracting more and more attent...
In this work, we propose a framework to learn a local regularization model for solving general image...
International audienceIn the usual non-local variational models, such as the non-local total variati...
International audienceIn the usual non-local variational models, such as the non-local total variati...
Sparse representation models code an image patch as a linear combination of a few atoms chosen out f...
Traditional patch-based sparse representation modeling of natural images usually suffer from two pro...
Abstract In image processing, sparse coding has been known to be relevant to both variational and Ba...
The COVID-19 pandemic has imposed to transform the face-to-face version of ECCV 2020 into an online ...
The COVID-19 pandemic has imposed to transform the face-to-face version of ECCV 2020 into an online ...
Group-based sparse representation (GSR) uses image nonlocal self-similarity (NSS) prior to grouping ...
Abstract—As a powerful statistical image modeling technique, sparse representation has been successf...
Patch based image modeling has achieved a great suc-cess in low level vision such as image denoising...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Several patch-based models have been proposed for image restoration in the literature. A common feat...
Image prior models based on sparse and redundant representations are attracting more and more attent...
In this work, we propose a framework to learn a local regularization model for solving general image...
International audienceIn the usual non-local variational models, such as the non-local total variati...
International audienceIn the usual non-local variational models, such as the non-local total variati...
Sparse representation models code an image patch as a linear combination of a few atoms chosen out f...
Traditional patch-based sparse representation modeling of natural images usually suffer from two pro...
Abstract In image processing, sparse coding has been known to be relevant to both variational and Ba...