Super-resolution from a single image

By Daniel Glasner, Shai Bagon, Michal Irani. 2009

2,022 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models

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

In Generative Models

Citations in the corpus

Non-local Neural Networks (2017, background): “Non-local matching is also the essence of successful texture synthesis [12], super-resolution [16], and inpainting [1] algorithms.”
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, background): “[17] the authors exploit patch redundancies across scales within the image to drive the SR.”
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]), edge-based 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].”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, methodology): “The goal of SISR methods is to recover a HR image from a single LR input image [14].”
Deep Image Prior (2017, methodology): “te PSNRs using center crops of the generated images (tables1and2). While our method is still outperformed by learning-based approaches, it does considerably better than the non-trained ones (bicubic, [19], [27]). Visually, it seems to close most of the gap between non-trained methods and state-of-th”
Image Super-Resolution Using Deep Convolutional Networks (2014, background): “In other words, it is an underdetermined inverse problem, of which solution is not unique.”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, methodology): “In recent years, popular approaches include exemplar-based 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].”
Enhanced Deep Residual Networks for Single Image Super-Resolution (2017, methodology): “Some approaches utilize image self-similarities to avoid using external databases [8, 6, 29], and increase the size of the limited internal dictionary by geometric transformation of patches [10].”
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (2017, methodology): “Several methods [9, 12] exploit the self-similarity property in natural images and construct LR-HR patch pairs based on the scale-space pyramid of the low-resolution input image.”
SinGAN: Learning a Generative Model From a Single Natural Image (2019, background): “Since small structures tend to recur across scales of natural scenes [17], at test time we upsample the LR image by a factor of r and inject it (together with noise) to the last generator, G0.”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “(d) Glasner09 [7] (e) Yang10 [8] (f) Dong11 [9]”
Flow-based Kernel Prior with Application to Blind Super-Resolution (2021, methodology): “In a single image, small image patches tend to recur across different scales [16, 57].”
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model (2019, methodology): “using only two cameras (Canon 5D3 and Nikon D810), the trained model generalizes well to other camera devices such as Sony a7II and mobile phones. 1. Introduction Single image super-resolution (SISR) [15] aims to recover a high-resolution (HR) image from its low-resolution (LR) observation. SISR has”
Learning a Deep Convolutional Network for Image Super-Resolution (2014, neutral): “These methods either exploit internal similarities of the same image [7,10,23], or learn mapping functions from external low- and high-resolution exemplar pairs [2,4,9,13,20,24,25,26,28].”
Nonlocally Centralized Sparse Representation for Image Restoration (2013, background): “For higher performance, the search of similar patches can also be carried out across different scales at the expense of higher computational complexity, as shown in [31].”
Image Super-Resolution via Deep Recursive Residual Network (2017, methodology): “posed inverse problem of Super Resolution (SR), and have demonstrated superiority over reconstruction-based methods [4, 35] or other learning paradigms [20, 22, 23, 31].”