Image super-resolution using gradient profile prior

By Jian Sun, Zongben Xu, Harry Shum. 2008

1,020 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, methodology): “[52] combine an edge-directed SR algorithm based on a gradient profile prior [50] with the benefits of learning-based detail synthesis.”
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): “Furthermore, while most existing methods [12], [15], [23], [29], [38], [39], [42], [46], [48], [52] are not readily extendable for handling multiple channels in color images, the proposed network can cope with three channels of color images simultaneously to achieve improved super-resolution perform”
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, background): “Previous studies [25, 23] adopted natural image statistics to the problem to reconstruct better high-resolution images.”
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].”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, background): “The high-resolution instance is produced by copying small patches from the most similar examples found in the training set (Freeman et al. (2002)).”
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].”
Anchored Neighborhood Regression for Fast Example-Based Super-Resolution (2013, methodology): “The latter use machine learning techniques and comprise methods like Gradient Profile Prior [13], which try to learn edge statistics from natural 0.01 0.1 1 10 100 28.1 28.2 28.3 28.4 28.5 28.6 28.7 28.8 Speed (1/s) PSNR (dB)”
Deep Learning for Single Image Super-Resolution: A Brief Review (2018, methodology): “Reconstructionbased SR methods [12], [13], [14], [15] often adopt sophisticated prior knowledge to restrict the possible solution space with an advantage of generating flexible and sharp details.”
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks (2016, neutral): “based [29]–[31], and learning-based methods [6], [9], [13].”
Fast Direct Super-Resolution by Simple Functions (2013, methodology): “Edge-specific priors focus on reconstructing sharp edges because they are important visual cues for image quality [2, 16].”
Super-resolution: a comprehensive survey (2014, methodology): “– [13], [138], [151], [180], [246], [286], [322], [367], [386],”
A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution (2014, background): “natural images consist mainly of flat regions separated by sharp edges) or statistical analysis of many natural images [2–5].”
On Single Image Scale-Up Using Sparse-Representations (2010, background): “While we do not provide a comprehensive review of these techniques, we refer the reader to the following papers [4,5,6,7,8,9,10,11].”
Single-Image Super-Resolution: A Benchmark (2014, methodology): “The formation is compatible with most SR methods [16,11,17,30,46,43,36] where the reconstructed images are well aligned with the ground truth images.”