Image super-resolution as sparse representation of raw image patches

By Jianchao Yang, John Wright, Thomas S. Huang, Yi Ma. 2008

1,672 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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, neutral): “Related approaches to the SR problem originate in compressed sensing and aim to estimate a sparse patch representation with respect to an over-complete dictionary [54, 9, 59].”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, methodology): “They group super-resolution techniques into prediction-based methods (bilinear, bicubic, Lanczos, [29]), edgebased methods [30,31], statistical methods [32–34], patch-based methods [30,35– 41], and sparse dictionary methods [42,43].”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “These methods either exploit internal similarities of the same image [5], [13], [16], [19], [47], or learn mapping functions from external low- and high-resolution exemplar pairs [2], [4], [6], [15], [23], [25], [37], [41], [42], [47], [48], [50], [51].”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, background): “Glasner [17] Kim [27] SCSR [60] SelfEx [22] SRCNN [8] PSyCo [40] VDSR [25] DRCN [26] ENet-E ENet-PAT I HR Figure 5.”
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (2017, methodology): “Numerous SR methods learn the LR-HR mapping with image pairs collected from external databases using supervised learning algorithms, such as nearest neighbor [10], manifold embedding [2, 5], kernel ridge regression [19], and sparse representation [37, 38, 39].”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, background): “Parametric models with sparse regularization have enjoyed great success in this problem (Elad & Aharon (2006); Yang et al. (2008)), thanks to their capacity to capture local regularity with efﬁcient convex optimization methods (Mairal et al. (2009)).”
Super-Resolution With Sparse Mixing Estimators (2010, background): “Dictionaries of image pat ches have also been studied for image interpolations with sparse representations [60], but with lit le PSNR improvements compared to bicubic interpolations.”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, background): “Prior to the deep-learning era, numerous super-resolution (SR) algorithms have been proposed based on the sampling theory [45], [46], edge-guided interpolation [47], [48], natu-ral image priors [49], [50], patch-exemplars [51], [52] and sparse representations [53], [54].”
Training-Free, Single-Image Super-Resolution Using a Dynamic Convolutional Network (2018, methodology): “[6], [7], who trained dictionaries for LR and HR image patches.”
Supervised translation-invariant sparse coding (2010, methodology): “The sparse representation has been successfully applied to many inverse problems, e.g., image restoration [17, 24], and also well applied to classiﬁcation tasks [23, 4, 25].”
Exploiting Aliasing for Manga Restoration (2021, methodology): “Traditional methods mainly leverage dictionary learning [29] or database retrieval[1, 4, 21] to reconstruct the highfrequency details for the low-resolution input.”
A New Pan-Sharpening Method Using a Compressed Sensing Technique (2011, background): “Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org.”
Image Super-Resolution Via Sparse Representation (2010, methodology): “A straightforward way to obtain two such dictionaries is to sample image patch pairs directly, which preserves the correspondence between the high resolution and low resolut ion patch items [33].”
Polynomial-Time Tensor Decompositions with Sum-of-Squares (2016, background): “Dictionary learning is an important problem in multiple areas, ranging from computational neuroscience [25]–[27], machine learning [28], [29], to computer vision and image processing [30]–[32].”
Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform (2018, methodology): “Contemporary SR algorithms are mostly learning-based methods, including neighbor embedding [4], sparse coding [49, 50, 45, 46] and random forest [39].”
Learning a Deep Convolutional Network for Image Super-Resolution (2014, methodology): “We show that the sparse-coding-based SR methods [25,26] can be viewed as a convolutional neural network.”