Non-local sparse models for image restoration

By Julien Mairal, Francis R. Bach, Jean Ponce, Guillermo Sapiro, Andrew Zisserman. 2009

1,854 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, background): “Traditional image denoising methods generally focus on modeling natural image priors and use the priors to restore the clean image, including sparse models [5, 26], Markov random field models [13], etc.”
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, methodology): “In particular, the NSS models are popular in state-of-the-art methods such as BM3D [2], LSSC [4], NCSR [6] and WNNM [13].”
End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling (2019, background): “, low-rank modeling [23], joint sparsity [24] and non-local means [25])”
Sparse representation or collaborative representation: Which helps face recognition? (2011, background): “…coded by structural primitives [1], and in recent years sparse coding or sparse representation has been widely studied to solve the inverse problems in various image restoration applications [2] [3], partially due to the progress of l 0 -norm and l 1 -norm minimization techniques [4] [5] [6].”
Spatial-Adaptive Network for Single Image Denoising (2020, neutral): “ribution of natural images or noise. With the distribution as the prior, they attempt to obtain clear images with optimization algorithms. The common priors include local smoothing [22, 30], sparsity [2, 19, 32], non-local self-similarity [5, 9, 8, 33, 11] and external statistical prior [40, 31]. No”
Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, background): “Recently many works have shown that the nonlocal redundancies existing in natural images are very useful for image restoration and a good combination of local sparsity and nonlocal redundancy can greatly enhance the performance of image reconstruction [3, 4, 18, 23].”
A Survey of Sparse Representation: Algorithms and Applications (2015, background): “[177] proposed a learned simultaneous sparse coding (LSSC) model, which integrated sparse dictionary learning and nonlocal self-similarities of natural images into a uni fied framework for image restoration.”
Infrared Patch-Image Model for Small Target Detection in a Single Image (2013, methodology): “…of non-local self-similarity also exists commonly in natural images, which motivates many well-known non-local methods, such as the non-local method for texture synthesis [37], the non-local algorithm for image denoising [38]–[40], the non-local sparse models for image restoration [41], and so on.”
Local features are not lonely – Laplacian sparse coding for image classification (2010, methodology): “successfully used simultaneously sparse coding to make all features response to a subset of the codebook in image restoration[15].”
From learning models of natural image patches to whole image restoration (2011, methodology): “Our method is clearly state-of-the-art when compared to generic priors, and is competitive with image based method such as BM3D and LLSC which are state-of-the-art in image denoising.”
Click Prediction for Web Image Reranking Using Multimodal Sparse Coding (2014, methodology): “Sparse coding is a popular signal processing method and performs well in many applications, e.g. signal reconstruction [11], signal decomposition [12], and signal denoising [13].”
Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation (2010, methodology): “in [11], reduces the number of training iterations required, and can substantially accelerate the process.”