Super-resolution: a comprehensive survey

By Kamal Nasrollahi, Thomas Baltzer Moeslund. 2014

670 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, methodology): “Recent overview articles on image SR include Nasrollahi and Moeslund [41] or Yang et al. [59].”
Amortised MAP Inference for Image Super-resolution (2016, methodology): “While SR has many applications in for example medical diagnostics or forensics (Nasrollahi & Moeslund, 2014, and references therein), here we are primarily motivated to improve the perceptual quality when applied to natural images.”
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (2016, neutral): “A large number of high-performing algorithms have since been proposed [35], see also the recent surveys by Nasrol-lahi and Moeslund [37] and Yang et al .”
Pixel Recursive Super Resolution (2017, background): “super resolution [31], colorization [50, 6], and depth estimation [37], models that are able to predict a single mode are heavily preferred over models that blend modes together.”
Video Enhancement with Task-Oriented Flow (2017, background): “n reconstruct the reference frame according to image formation models for frame interpolation [2, 33, 36], video super-resolution [17], and denoising [15, 30, 20]. We refer readers to survey articles [23, 8] for comprehensive literature reviews on these ﬂourishing research topics. Deep Learning for ”
Deep Learning for Image Super-Resolution: A Survey (2019, neutral): “Although there are some existing SR surveys in literature, our work differs in that we are focused in deep learning based SR techniques, while most of the earlier works [33], [34], [35], [36] aim at surveying traditional SR algorithms or some studies mainly concentrate on providing quantitative eval”
Blind image super-resolution with spatially variant degradations (2019, methodology): “A detailed review and evaluation of SR state of the art can be found in the survey realized by Nasrollahi and Moeslund [2014] and the benchmark proposed by Yang et al. [2014].”
Image super-resolution: The techniques, applications, and future (2016, background): “Early review papers have provided specific descriptions and explanations of those methods [4,8,14].”
Enhancing Image Quality via Style Transfer for Single Image Super-Resolution (2018, background): “SISR has attracted extensive attention from both academic and industrial communities and has wide applications in fields like medical imaging, infrared imaging, and face recognition [2]–[5].”
Perceptual Adversarial Networks for Image-to-Image Transformation (2017, background): “More examples include, but not limited to, image de-noising [1], image in-painting [2], image super-resolution [3], image colorization [4], image segmentation [5], etc .”
Image Super-Resolution by Neural Texture Transfer (2019, background): “The reader could refer to [29, 38] for more comprehensive review.”
Frame-Recurrent Video Super-Resolution (2018, methodology): “We refer the reader to Milanfar [28] and Nasrollahi and Moeslund [29] for extensive overviews of prior art up to recent years.”