Super-Resolution With Sparse Mixing Estimators

By Stéphane Mallat, G. Yu. IEEE Transactions on Image Processing, 2010

329 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3ff937d1b94f6d5fc0df9ff76821604c4df4bce7

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

A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution (2014, background): “Models that are commonly exploited in single image SR methods include image smoothness and geometric regularity of image structures [3]), gradient profile priors [4], self-similarity of image patches within and across different scales in the same image [6], [7], [24], and sparsity – either in the wa”
On Single Image Scale-Up Using Sparse-Representations (2010, result): “is the approach taken, for example, in [18,19], and this explains why we cannot compare our results to theirs.”
An introduction to continuous optimization for imaging (2016, methodology): “…they are closely related to methods based on structured sparsity (Danielyan, Katkovnik and Egiazarian 2012) or (patch-based) Gaussian mixture models (Mallat and Yu 2010, Yu, Sapiro and Mallat 2012, Lebrun, Buades and Morel 2013) and can be given a ‘variational’ form (Gilboa, Darbon, Osher and…”
Accurate Blur Models vs. Image Priors in Single Image Super-resolution (2013, background): “Examples include antialiasing with bicubic interpolation (Matlab’s default imresize function) [8, 27], Gaussian blur [3], Gaussian blur followed by bicubic interpolation [7], simple pixel averaging [5], and sampling without any pre-smoothing [15].”
Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, methodology): “In [21], a series of linear inverse estimators of HR image are computed based on different priors on the image regularity.”
Super-resolution: a comprehensive survey (2014, methodology): “In [162,302,320,346,400, 437,448,477,550,565,566], but the results obtained by DWT are used as a regularization term in maximum a posteriori (MAP) formulation of the problem (Sect.”
A Survey of Sparse Representation: Algorithms and Applications (2015, methodology): “Mallat and Yu [164] proposed a sparse mixing estimator for image super-resolution, which introduced an adaptive estimator models by combining a grou p of linear inverse estimators based on different prior knowl edge for sparse representation.”
Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement (2011, methodology): “This category of prior generally regularizes the first or higher order derivatives of image which implies the smoothness of image edges.”
Nonparametric Blind Super-resolution (2013, methodology): “Most SR methods (e.g. [11] [7] [2] [4] [20] [16] [15] [21]) assume that the low-resolution input image was obtained by down-sampling the unknown high-resolution image with a known blur kernel.”