Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior

By Kwang In Kim, Younghee Kwon. 2010

993 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, background): “In Kim and Kwon [33] the authors emphasize the tendency of neighborhood approaches to overfit and formulate a more general map of example pairs using kernel ridge regression.”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, methodology): “They group super-resolution techniques into prediction-based methods (bilinear, bicubic, Lanczos, [24]), edgebased methods [25,26], statistical methods [27,28,29], patch-based methods [25,30,31,32,33,34,35,36], and sparse dictionary methods [37,38].”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “Motivated by this fact, we consider a convolutional neural network that directly learns an end-to-end mapping between low- and high-resolution images.”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, background): “In recent years, popular approaches include exemplarbased models that either exploit recurrent patches of different scales within a single image [13, 17, 22, 56] or learn mappings between low and high resolution pairs of image patches in external databases [3, 5, 14, 27, 51, 58, 63].”
Accurate Image Super-Resolution Using Very Deep Convolutional Networks (2015, methodology): “Early methods include interpolation such as bicubic interpolation and Lanczos resampling [7] more powerful methods utilizing statistical image priors [20, 13] or internal patch recurrence [9].”
Deeply-Recursive Convolutional Network for Image Super-Resolution (2015, methodology): “Some of the more powerful methods utilize statistical image priors [27, 12] or internal patch recurrence [8, 10].”
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].”
Pixel Recursive Super Resolution (2017, background): “Enhancing linear methods with rich image priors such as sparsity [2] or Gaussian mixtures [51] have substantially improved the quality of the methods; likewise, leveraging low-level image statistics such as edge gradients improves predictions [47, 41, 8, 16, 39, 22].”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “Numerous single-image SR algorithms have been recently proposed for generic images that exploit priors based on edges [1], gradients [2, 3], neighboring interpolation [4, 5], regression [6], and patches [7, 8, 9, 10, 11, 12, 13, 14, 15].”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, background): “methods. Super-resolution (SR). Prior to the deep-learning era, numerous SR algorithms have been proposed based on the sampling theory [55,53], edge-guided interpolation [4,122], natural image priors [58,110], patch-exemplars [15,33] and sparse representations [114,113]. Currently, deep-learning tec”
Deep Generalized Unfolding Networks for Image Restoration (2022, background): “, [7,12,17,25,32,56]) usually formulate IR as a Bayesian problem, solving Eq.”
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks (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 [23], manifold embedding [24], [25], kernel ridge regression [26], and sparse representation [1], [2], [27].”
Learning a Deep Convolutional Network for Light-Field Image Super-Resolution (2015, methodology): “For image super-resolution (SR), most conventional way is to perform optimizations with prior information [16, 26].”
Single image super-resolution from transformed self-exemplars (2015, methodology): “The algorithms we use are: Kernel rigid regression (Kim) [23], sparse coding (ScSR) [41], adjusted anchored neighbor neighbor regression (A+) [34], and convolutional neural networks (SR- CNN) [9].”
Multi-Stage Progressive Image Restoration (2021, positive): “In order to restrict the solution space to valid/natural images, existing restoration techniques [19, 29, 39, 59, 66, 67, 100] explicitly use image priors that are handcrafted with empirical observations.”
Deeply Improved Sparse Coding for Image Super-Resolution (2015, methodology): “Analytical priors, such as bicubic interpolation, work well for smooth regions; while image models based on statistics of edges [9] and gradients [15, 1] can recover sharper structures.”
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, methodology): “The overﬁtting tendency of neighborhood approaches was pointed out by [25] while also formulating a more generic approach using kernel ridge regression.”
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model (2019, background): “Since SISR is a severely ill-posed inverse problem, learning image prior information from the HR and/or LR exemplar images [15, 13, 55, 19, 14, 7, 24, 56, 11, 20, 46, 41] plays an indispensable role in recovering the details from an LR input image.”