Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

By Radu Timofte, Vincent De Smet, Luc Van Gool. 2013

1,282 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

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): “Neighborhood embedding approaches upsample a given LR image patch by finding similar LR training patches in a low dimensional manifold and combining their corresponding HR patches for reconstruction [45, 46].”
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].”
Image Super-Resolution Using Deep Convolutional Networks (2014, methodology): “In other words, it is an underdetermined inverse problem, of which solution is not unique.”
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.”
Deeply-Recursive Convolutional Network for Image Super-Resolution (2015, methodology): “For this reason, several super-resolution methods [28, 29, 19, 2] predict image details only.”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “(g) Yang13 [12] (h) Timofte13 [14] (i) SRCNN [6]”
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes (2016, methodology): “We compare with two state-of-the-art single image super-resolution methods, A+ (Timofte et al., 2013) and SRCNN (Dong et al.”
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.”
Exploiting Aliasing for Manga Restoration (2021, methodology): “Traditional methods mainly leverage dictionary learning [29] or database retrieval[1, 4, 21] to reconstruct the highfrequency details for the low-resolution input.”
Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network (2018, methodology): “le dictionary. HR images from the web with similar contents were used with-in a structure-aware matching criterion to super-resolve landmark images in [48]. The class of neighbor embedding approaches [8,3,17,44,45] aim to nd similar looking LR training patches from a low dimensional manifold and the”
Learning Continuous Image Representation with Local Implicit Image Function (2020, background): “low-resolution inputs, which is related to the image superresolution tasks [5, 46, 44, 9, 23, 24, 22, 51, 49].”
Depth Map Super-Resolution by Deep Multi-Scale Guidance (2016, methodology): “improved sparse-coding method by introducing the anchored neighborhood regression [18].”
Seven Ways to Improve Example-Based Single Image Super Resolution (2015, methodology): “In general, if the dictionary size (basis of samples/anchoring points) is increased, the performance for sparse coding (such as Zeyde [41] or Yang [40]) or anchored methods (such as ANR [30] or A+ [31]) improves as the learned model generalizes better, as shown in Fig.”
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration (2020, neutral): “IPAL Dataset for Perceptual Image Restoration 11 Method Year PSNR " SSIM " Ma " NIQE # PI # LPIPS # MOS " YY [52] 2013 23.358 0.68977 4.548610 6.4174 85.93447 0.357412 1367.71 TSG [45] 2013 23.55 70.67758 4.129812 6.4163 6.143310 0.357011 1387.247 A+ [46] 2014 23.82 60.6919 4.385”
Learning a Deep Convolutional Network for Image Super-Resolution (2014, methodology): “A category of state-of-the-art SR approaches [9,4,25,26,24,2,28,20] learn a mapping between low/high-resolution patches.”
PSyCo: Manifold Span Reduction for Super Resolution (2016, methodology): “For each atom di in Dl, a certain neighborhood or cluster Nil is found through a nearest neighbor (NN) search from a training pool of examples, which in ANR is the same Dl.”
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.”
Image Super-Resolution by Neural Texture Transfer (2019, background): “There are existing RefSR approaches [8, 3, 7, 33, 39, 34, 27, 41] that adopt internal examples (self-example) or external highfrequency information to enhance textures.”
A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution (2014, methodology): “Compared Methods We compare with all the methods of [1] under the same conditions as originally compared with ANR.”