Super resolution using edge prior and single image detail synthesis

By Yu-Wing Tai, Shuaicheng Liu, Michael S. Brown, Stephen Lin. 2010

345 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): “Photo-realistic image super-resolution techniques including [44, 60, 57] have been focusing on minimizing the perceptual differences by using detail synthesis, a multi-scale dictionary or a structure aware loss function.”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, background): “Thus far, realistic textures in the context of high-magniﬁcation SISR have only been achieved by user-guided methods [19, 50].”
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.”
Single-Image Super-Resolution: A Benchmark (2014, background): “While domain-specific SISR algorithms focus on specific classes of images such as faces [35,42], scenes [33], and graphics artwork [18], generic SISR algorithms [10,38,8,3,27,30,11,46,9,34,32,12,5,39,44,43] are developed for all kinds of images where the priors are typically based on primitive image”
Multi-scale dictionary for single image super-resolution (2012, methodology): “Reconstruction-based methods (e.g., [11] [13]) estimate an HR image by incorporating a certain prior knowledge (e.g., edge prior [14], redundancy of similarity prior [19], and gradient profile prior [13]) to make SR estimate well-posed.”
Multilevel and Multiscale Network for Single-Image Super-Resolution (2019, methodology): “These methods were popular in the past few years [8], [9].”
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, methodology): “ional sparse coding framework in [19] process the whole image and exploits the consistency of neighboring patches to yield better image reconstruction. To generate edge-preserving realistic textures, [42] employed a learning-based approach driven by a gradient prole prior. [30] tried to capture the ”
Fast Direct Super-Resolution by Simple Functions (2013, background): “Exemplar images contain abundant visual information which can be exploited to enrich the superresolution (SR) image details [4, 1, 5, 19, 6, 17, 3, 18].”
Convolutional Sparse Coding for Image Super-Resolution (2015, methodology): “Inspired by [8], many methods have been developed to model prior knowledge on local structures or patches using natural images [4, 7, 19, 29].”
Image Super Resolution Based on Fusing Multiple Convolution Neural Networks (2017, background): “Later, structural and shape prior are introduced to enhance these interpolations [5][6][24].”
Super-resolution: a comprehensive survey (2014, neutral): “[4], [57], [58], [71], [82], [85], [99], [100], [127], [133], [142], [154], [165], [187], [208], [235], [241], [250], [281], [285], [327] [340], [341], [343], [344], [354], [360], [372], [373], [379], [382], [394], [396], [400], [402], [403], [404], [409], [425], [430], [434], [435], [442], [443], [”
Accurate Blur Models vs. Image Priors in Single Image Super-resolution (2013, background): “Developing sophisticated image priors has been the focus of much single image SR research in the past decade, with many significant successes [7, 20, 23, 8, 6, 9, 21, 27, 25, 5, 19, 22, 1, 8, 13].”
Single image super-resolution using Gaussian process regression (2011, methodology): “To further inspect the effectiveness of our method, we show a comparison of our large 10× SR result to that of the single image detail synthesis with edge prior method from [20] in Figure 7(a) and Figure 7(b).”