Y. Romano, J. Isidoro, and P. Milanfar. (2016)cite arxiv:1606.01299Comment: Supplementary material can be found at https://goo.gl/D0ETxG.
Abstract
Given an image, we wish to produce an image of larger size with significantly
more pixels and higher image quality. This is generally known as the Single
Image Super-Resolution (SISR) problem. The idea is that with sufficient
training data (corresponding pairs of low and high resolution images) we can
learn set of filters (i.e. a mapping) that when applied to given image that is
not in the training set, will produce a higher resolution version of it, where
the learning is preferably low complexity. In our proposed approach, the
run-time is more than one to two orders of magnitude faster than the best
competing methods currently available, while producing results comparable or
better than state-of-the-art.
A closely related topic is image sharpening and contrast enhancement, i.e.,
improving the visual quality of a blurry image by amplifying the underlying
details (a wide range of frequencies). Our approach additionally includes an
extremely efficient way to produce an image that is significantly sharper than
the input blurry one, without introducing artifacts such as halos and noise
amplification. We illustrate how this effective sharpening algorithm, in
addition to being of independent interest, can be used as a pre-processing step
to induce the learning of more effective upscaling filters with built-in
sharpening and contrast enhancement effect.
Description
[1606.01299] RAISR: Rapid and Accurate Image Super Resolution
%0 Generic
%1 romano2016raisr
%A Romano, Yaniv
%A Isidoro, John
%A Milanfar, Peyman
%D 2016
%K 2016 arxiv image-processing paper super-resolution
%T RAISR: Rapid and Accurate Image Super Resolution
%U http://arxiv.org/abs/1606.01299
%X Given an image, we wish to produce an image of larger size with significantly
more pixels and higher image quality. This is generally known as the Single
Image Super-Resolution (SISR) problem. The idea is that with sufficient
training data (corresponding pairs of low and high resolution images) we can
learn set of filters (i.e. a mapping) that when applied to given image that is
not in the training set, will produce a higher resolution version of it, where
the learning is preferably low complexity. In our proposed approach, the
run-time is more than one to two orders of magnitude faster than the best
competing methods currently available, while producing results comparable or
better than state-of-the-art.
A closely related topic is image sharpening and contrast enhancement, i.e.,
improving the visual quality of a blurry image by amplifying the underlying
details (a wide range of frequencies). Our approach additionally includes an
extremely efficient way to produce an image that is significantly sharper than
the input blurry one, without introducing artifacts such as halos and noise
amplification. We illustrate how this effective sharpening algorithm, in
addition to being of independent interest, can be used as a pre-processing step
to induce the learning of more effective upscaling filters with built-in
sharpening and contrast enhancement effect.
@misc{romano2016raisr,
abstract = {Given an image, we wish to produce an image of larger size with significantly
more pixels and higher image quality. This is generally known as the Single
Image Super-Resolution (SISR) problem. The idea is that with sufficient
training data (corresponding pairs of low and high resolution images) we can
learn set of filters (i.e. a mapping) that when applied to given image that is
not in the training set, will produce a higher resolution version of it, where
the learning is preferably low complexity. In our proposed approach, the
run-time is more than one to two orders of magnitude faster than the best
competing methods currently available, while producing results comparable or
better than state-of-the-art.
A closely related topic is image sharpening and contrast enhancement, i.e.,
improving the visual quality of a blurry image by amplifying the underlying
details (a wide range of frequencies). Our approach additionally includes an
extremely efficient way to produce an image that is significantly sharper than
the input blurry one, without introducing artifacts such as halos and noise
amplification. We illustrate how this effective sharpening algorithm, in
addition to being of independent interest, can be used as a pre-processing step
to induce the learning of more effective upscaling filters with built-in
sharpening and contrast enhancement effect.},
added-at = {2019-03-14T20:07:15.000+0100},
author = {Romano, Yaniv and Isidoro, John and Milanfar, Peyman},
biburl = {https://www.bibsonomy.org/bibtex/2f9fa61812505fc7711cc2bc16fcff5e4/analyst},
description = {[1606.01299] RAISR: Rapid and Accurate Image Super Resolution},
interhash = {b8eb5189385a171c397e8a10653aa567},
intrahash = {f9fa61812505fc7711cc2bc16fcff5e4},
keywords = {2016 arxiv image-processing paper super-resolution},
note = {cite arxiv:1606.01299Comment: Supplementary material can be found at https://goo.gl/D0ETxG},
timestamp = {2019-03-14T20:07:15.000+0100},
title = {RAISR: Rapid and Accurate Image Super Resolution},
url = {http://arxiv.org/abs/1606.01299},
year = 2016
}