On Single Image Scale-Up Using Sparse-Representations

By Roman Zeyde, Michael Elad, Matan Protter. 2010

3,781 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, methodology): “Mean opinion score (MOS) testing In all conducted MOS tests we have asked 26 human raters to assign a score from 1 (Bad) to 5 (Excellent) to reconstructions of the 4× downsampled versions of images from Set5, Set14 and BSD100.”
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (2016, methodology): “We evaluate all models on the standard Set5 [60], Set14 [61], and BSD100 [41] datasets.”
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks (2020, neutral): “, 2012), Set14 (Zeyde et al., 2010), BSD100 (Martin et al.”
Hierarchical Neural Architecture Search for Single Image Super-Resolution (2020, methodology): “To show the effectiveness of out method, we conduct comparisons on ﬁve benchmark datasets, including Set5 [36], Set14 [37], BSD100 [38], Urban100 [39], and Manga109 [40].”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, methodology): “We evaluate the run time of other methods [2, 51, 39] from the Matlab codes provided by [40] and [31].”
Deep Image Prior (2017, methodology): “Also in this group are methods based on fitting dictionaries to the patches of the corrupted image [23, 32] as well as methods based on convolutional sparse coding [31], which can also fit statistical models similar to shallow ConvNets to the reconstructed image [25].”
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].”
Accurate Image Super-Resolution Using Very Deep Convolutional Networks (2015, methodology): “Sparse coding [25, 26, 21, 22] methods use a learned compact dictionary based on sparse signal representation.”
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (2018, methodology): “We evaluate our models on widely used benchmark datasets – Set5 [4], Set14 [43], BSD100 [28], Urban100 [17], and the PIRM self-validation dataset that is provided in the PIRM-SR Challenge.”
Deeply-Recursive Convolutional Network for Image Super-Resolution (2015, methodology): “This is achieved with various techniques: neighbor embedding [4, 19], sparse coding [31, 32, 28, 29], convolutional neural network (CNN) [5] and random forest [23].”
Enhanced Deep Residual Networks for Single Image Super-Resolution (2017, methodology): “We also compare the performance on four standard benchmark datasets: Set5 [2], Set14 [33], B100 [17], and Urban100 [10].”
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (2017, methodology): “Figure 6 shows the trade-offs between the run time and performance (in terms of PSNR) on SET14 for 4× SR.”
Image Super-Resolution Using Very Deep Residual Channel Attention Networks (2018, neutral): “For testing, we use five standard benchmark datasets: Set5 [36], Set14 [37], B100 [38], Urban100 [22], and Manga109 [39].”
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes (2016, methodology): “We report the average test results, utilizing the standard metrics PSNR and SSIM (Wang et al., 2004), on two standard test datasets Set14 (Zeyde et al., 2010) and BSD200 (Martin et al., 2001).”
Target-Adaptive CNN-Based Pansharpening (2017, methodology): “In [56], [57], it was used for dictionary-based superresolution, proving effective both in terms of accuracy and training speed.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, background): “Some earlier classical datasets include Set5 [49], Set14 [50], and LIVE1 [51].”
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution (2015, background): “Yang et al. [25] and Zeyde et al. [26] exploit compressive sensing to encode image patches with a compact dictionary and obtain sparse representations.”