Response to the Comments on "Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation'

By Zhouchen Lin, Harry Shum. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

311 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/63442f444a33b3e21bd8b14aa68765939ee9d7f1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computational Mechanics

In Signal Processing

Citations in the corpus

Natural image denoising: Optimality and inherent bounds (2011, background): “Similarly, limits on the related problem of superresolution have been derived in the past [1, 16], but they again account for the numerical stability of the linear system being inverted, and do not model the additional gain provided by natural image priors.”
Super-resolution from a single image (2009, background): “Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution.”
Distillation (2010, unknown): “…& Scholkopf, 2004), and the multi-frame cases (Baker & Kanade, 2002; Ben-Ezra, Zhouchen, & Wilburn, 2007; Freeman, Jones, & Pasztor, 2002; Freeman, Pasztor, & Carmichael, 2000; Lin & Shum, 2004; Pickup, Capel, Roberts, & Zisserman, 2006; Pickup, Roberts, & Zisserman, 2006; Tipping & Bishop, 2002).”
Studying Very Low Resolution Recognition Using Deep Networks (2016, background): “They are otherwise prone to be overlooked from LR images.”
Ultra-Resolving Face Images by Discriminative Generative Networks (2016, methodology): “Image statistics based methods employ natural image priors to predict HR images, but they are limited to smaller scaling factors [27].”
Super‐resolution methods in MRI: Can they improve the trade‐off between resolution, signal‐to‐noise ratio, and acquisition time? (2012, background): “This can be attributed to the fact that SRR is highly dependent on accurate registration of the LR images (18,19), and in brain MRI a simple global motion model can be applied.”
Super resolution using edge prior and single image detail synthesis (2010, methodology): “, [13, 20, 26, 17, 25, 6, 3, 23, 22]) estimate an SR image by enforcing some prior knowledge on the upsampled image (e.”
A survey on super-resolution imaging (2011, unknown): “studied a numerical perturbation model of reconstruction-based SR algorithms for the case of translational motion [31] and the learning-based SR algorithms [32].”