Advances and challenges in super‐resolution

By Sina Farsiu, M. Dirk Robinson, Michael Elad, Peyman Milanfar. International journal of imaging systems and technology (Print), 2004

681 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/fea09351806ff3ddb21eb74f60928d904941e3f9

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

A survey on super-resolution imaging (2011, background): “Super-resolution (SR) imaging [1–20] aims to overcome or compensate the limitation or shortcomings of the image acquisition device/system and/or possibly ill-posed acquisition conditions to produce a higher-resolution image based”
Deep Unfolding Network for Image Super-Resolution (2020, background): “Ac-tually, for a scale factor of s , the classical (traditional) degradation model of SISR [17, 18, 37] assumes the LR image y is a blurred, decimated, and noisy version of an HR image x .”
The Cosparse Analysis Model and Algorithms (2011, neutral): “Empirically, analysis models have been successfully used for a variety of signal processing tasks [24, 30, 48, 49, 50] such as denoising, deblurring, and most recently compressed sensing, but this has been done with little theoretical justification.”
Flow-based Kernel Prior with Application to Blind Super-Resolution (2021, methodology): “Generally, the classical degradation model of image SR [12, 13, 31] assumes the LR image y is obtained via a composition of blurring and downsampling from the HR image x.”
Medical Image Synthesis with Deep Convolutional Adversarial Networks (2018, background): “However, medical image synthesis is very challenging to solve directly since the mapping from the source image to the target image (or its inverse) is usually of high dimensionality and ill-posed [5]–[7].”
The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution (2012, background): “This approach relates to a large bulk of image processing literature [14], [15], [16], [17], [18], [19].”
ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis (2021, background): “images for a subject given source-modality images acquired under a limited scan budget [7].”
A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution (2014, neutral): “The classical image SR problem is cast as fusing multiple LR images of the same scene obtained at subpixel misalignments into one HR image (for a comprehensive review see [1] and [2]).”
Super-Resolution With Sparse Mixing Estimators (2010, methodology): “Super-resolution interp olations can further be improved by using a sequence of images [48], [30], [31], [46], [27] or a compari son dataset [28], [22], [58] to perform the interpolation.”
Non-local Regularization of Inverse Problems (2008, background): “It is usually applied to a sequence of images in video, see the review papers [43, 27].”
Blind deconvolution in scientific imaging & computational photography (2011, methodology): “, 2003; Farsiu et al., 2004). However, most of these works are based on the assumption that the blur is known, and only a few deal with the harder case of blind super-resolution. The work most closely related to ours is Šroubek et al. (2007), who propose a unifying framework that simultaneously perf”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “Numerous single-image SR algorithms have been recently proposed for generic images that exploit priors based on edges [1], gradients [2, 3], neighboring interpolation [4, 5], regression [6], and patches [7, 8, 9, 10, 11, 12, 13, 14, 15].”
Generalizing the Nonlocal-Means to Super-Resolution Reconstruction (2009, result): “The idea of breaking the super-resolution task into two parts—fusing the inputs and then deblurring—has been suggested previously in [13], [18], [20], and [ 21 ].”