Fast image/video upsampling

By Qi Shan, Zhaorong Li, Jiaya Jia, Chi-Keung Tang. ACM Transactions on Graphics, 2008

342 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f4b9c480f794909195605c1c7960b98489cba2e8

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

Citations in the corpus

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].”
Single image super-resolution using Gaussian process regression (2011, background): “, [2, 11, 15, 18, 10]) apply various smoothness priors (e.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 on Bayesian Adaptive Video Super Resolution (methodology): “In-depth experiments demonstrate that our system outperforms the state-of-the-art super resolution systems [1], [31], [36] on challenging real-world sequences.”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “Glasner09 [7] Shan08 [2] Shan08 [2] Yang13 [12] 0.”
Fast Direct Super-Resolution by Simple Functions (2013, methodology): “(e) Back Projection [8] (f) Shan [15] (g) Yang [24] (h) Wang [3]”
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution (2015, methodology): “(a) Input (b) Bicubic (c) FUS [39] (d) Enhancer [1] (e) DeepSR [28] (f) BRCN”
Single-Image Super-Resolution: A Benchmark (2014, methodology): “There are several ways to generate LR test images from the ground truth images [27,30,36] such that the generated LR test images may be numerically different.”
Super resolution using edge prior and single image detail synthesis (2010, background): “, [13, 20, 26, 17, 25, 6, 3, 23, 22]) estimate an SR image by enforcing some prior knowledge on the upsampled image (e.”
On Bayesian Adaptive Video Super Resolution (2014, methodology): “In-depth experiments demonstrate that our system outperforms the state-of-the-art super resolution systems [1], [31], [36] on challenging real-world sequences.”
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: a comprehensive survey (2014, methodology): “These algorithms [138,202,279,286,287,362,368,394,407, 431,445,500,520,546] similar to their peer multiple imagebased SR algorithms try to address the aliasing artifacts that”