$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

By Michal Aharon, Michael Elad, Alfred Marcel Bruckstein. IEEE Transactions on Signal Processing, 2006

8,032 citations recorded by the source corpus.

Subfields: Computational Mechanics, Mechanics of Materials, Signal Processing

View Paper: https://www.semanticscholar.org/paper/83b522f4bfa5db7f7d34f839475af7d078107634

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 Mechanics of Materials

In Signal Processing

Citations in the corpus

A Unified Algorithmic Framework for Block-Structured Optimization Involving Big Data: With applications in machine learning and signal processing (2015, methodology): “[80] M.”
Spatial-Adaptive Network for Single Image Denoising (2020, neutral): “Many of the earlier model-based methods find natural image priors and then apply optimization algorithms to solve the model iteratively [22, 2, 30, 40].”
Example Selection For Dictionary Learning (2014, methodology): “For instance, K-SVD Aharon et al. (2006) relies upon identifying a group of examples that use a particular dictionary element during its update stage.”
Solving Linear Inverse Problems Using Gan Priors: An Algorithm with Provable Guarantees (2018, methodology): “In [6, 7], sparse and redundant dictionaries are learned for image denoising, whereas in [25, 26, 8], total variation is used as a regularizer.”
New Algorithms for Learning Incoherent and Overcomplete Dictionaries (2013, methodology): “This requires having the right dictionary A ∈ Rn×m for the dataset, which allows each data point to be written as a sparse linear combination of the columns of A.”
Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network (2017, methodology): “K-SVD could not remove all the noise and sometimes make the resultant image very blocky.”
Anchored Neighborhood Regression for Fast Example-Based Super-Resolution (2013, methodology): “The most important changes include using different training approaches for the dictionary pair (K-SVD [1] for the low resolution dictionary and direct approach using the pseudoinverse for the high resolution dictionary), performing dimensionality reduction on the patches through PCA and using Orthog”
Deep Learning on Image Denoising: An overview (2019, neutral): “R (dB) of different methods on the DND for real-noisy image denoising. Methods DND EPLL [274] 33.51 TNRD [35] 33.65 NCSR [49] 34.05 MLP [25] 34.23 BM3D [45] 34.51 FoE [181] 34.62 WNNM [69] 34.67 KSVD [6] 36.49 CDnCNN-B [258] 32.43 FFDNet [260] 34.40 MCWNNM [137] 37.38 TWSC [232] 37.94 GCBD [31] 35.5”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “l network. An overview of the network is depicted in Figure 2. Next we detail our deﬁnition of each operation. 3.1.1 Patch extraction and representation A popular strategy in image restoration (e.g., [1]) is to densely extract patches and then represent them by a set of pre-trained bases such as PCA”
Compressed Sensing for Wireless Communications: Useful Tips and Tricks (2015, background): “to a dictionary having many more columns than rows. Since such dictionary is usually unknown beforehand, it should learned from a set of training data. This task is known as dictionary learning [24], [25]. Assume for a set of speciﬁc signals xi ∈ CN×1, we want to learn an overcomplete dictionary D ∈”