A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations. Adler, A., Hel-Or, Y., & Elad, M. In Daniilidis, K., Maragos, P., & Paragios, N., editors, Computer Vision – ECCV 2010, of Lecture Notes in Computer Science, pages 622–635, Berlin, Heidelberg, 2010. Springer. TLDR: A novel approach for online shrinkage functions learning in single image super-resolution that leverages the classical Wavelet Shrinkage denoising technique and demonstrates superior performance compared to state-of-the-art results.doi abstract bibtex We present a novel approach for online shrinkage functions learning in single image super-resolution. The proposed approach leverages the classical Wavelet Shrinkage denoising technique where a set of scalar shrinkage functions is applied to the wavelet coefficients of a noisy image. In the proposed approach, a unique set of learned shrinkage functions is applied to the overcomplete representation coefficients of the interpolated input image. The super-resolution image is reconstructed from the post-shrinkage coefficients. During the learning stage, the low-resolution input image is treated as a reference high-resolution image and a super-resolution reconstruction process is applied to a scaled-down version of it. The shapes of all shrinkage functions are jointly learned by solving a Least Squares optimization problem that minimizes the sum of squared errors between the reference image and its super-resolution approximation. Computer simulations demonstrate superior performance compared to state-of-the-art results.
@inproceedings{adler_shrinkage_2010,
address = {Berlin, Heidelberg},
series = {Lecture {Notes} in {Computer} {Science}},
title = {A {Shrinkage} {Learning} {Approach} for {Single} {Image} {Super}-{Resolution} with {Overcomplete} {Representations}},
isbn = {978-3-642-15552-9},
doi = {10.1007/978-3-642-15552-9_45},
abstract = {We present a novel approach for online shrinkage functions learning in single image super-resolution. The proposed approach leverages the classical Wavelet Shrinkage denoising technique where a set of scalar shrinkage functions is applied to the wavelet coefficients of a noisy image. In the proposed approach, a unique set of learned shrinkage functions is applied to the overcomplete representation coefficients of the interpolated input image. The super-resolution image is reconstructed from the post-shrinkage coefficients. During the learning stage, the low-resolution input image is treated as a reference high-resolution image and a super-resolution reconstruction process is applied to a scaled-down version of it. The shapes of all shrinkage functions are jointly learned by solving a Least Squares optimization problem that minimizes the sum of squared errors between the reference image and its super-resolution approximation. Computer simulations demonstrate superior performance compared to state-of-the-art results.},
language = {en},
booktitle = {Computer {Vision} – {ECCV} 2010},
publisher = {Springer},
author = {Adler, Amir and Hel-Or, Yacov and Elad, Michael},
editor = {Daniilidis, Kostas and Maragos, Petros and Paragios, Nikos},
year = {2010},
note = {TLDR: A novel approach for online shrinkage functions learning in single image super-resolution that leverages the classical Wavelet Shrinkage denoising technique and demonstrates superior performance compared to state-of-the-art results.},
keywords = {\#Analysis, \#ECCV{\textgreater}10, \#Representation{\textgreater}SR, \#Vision, /unread, Image Degradation Model, Noisy Image, Overcomplete Representation, Shrinkage Function, Sparse Representation, ⭐⭐⭐⭐},
pages = {622--635},
}
Downloads: 0
{"_id":"44ZjWH4mrqZSwYfYD","bibbaseid":"adler-helor-elad-ashrinkagelearningapproachforsingleimagesuperresolutionwithovercompleterepresentations-2010","author_short":["Adler, A.","Hel-Or, Y.","Elad, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Berlin, Heidelberg","series":"Lecture Notes in Computer Science","title":"A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations","isbn":"978-3-642-15552-9","doi":"10.1007/978-3-642-15552-9_45","abstract":"We present a novel approach for online shrinkage functions learning in single image super-resolution. The proposed approach leverages the classical Wavelet Shrinkage denoising technique where a set of scalar shrinkage functions is applied to the wavelet coefficients of a noisy image. In the proposed approach, a unique set of learned shrinkage functions is applied to the overcomplete representation coefficients of the interpolated input image. The super-resolution image is reconstructed from the post-shrinkage coefficients. During the learning stage, the low-resolution input image is treated as a reference high-resolution image and a super-resolution reconstruction process is applied to a scaled-down version of it. The shapes of all shrinkage functions are jointly learned by solving a Least Squares optimization problem that minimizes the sum of squared errors between the reference image and its super-resolution approximation. Computer simulations demonstrate superior performance compared to state-of-the-art results.","language":"en","booktitle":"Computer Vision – ECCV 2010","publisher":"Springer","author":[{"propositions":[],"lastnames":["Adler"],"firstnames":["Amir"],"suffixes":[]},{"propositions":[],"lastnames":["Hel-Or"],"firstnames":["Yacov"],"suffixes":[]},{"propositions":[],"lastnames":["Elad"],"firstnames":["Michael"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Daniilidis"],"firstnames":["Kostas"],"suffixes":[]},{"propositions":[],"lastnames":["Maragos"],"firstnames":["Petros"],"suffixes":[]},{"propositions":[],"lastnames":["Paragios"],"firstnames":["Nikos"],"suffixes":[]}],"year":"2010","note":"TLDR: A novel approach for online shrinkage functions learning in single image super-resolution that leverages the classical Wavelet Shrinkage denoising technique and demonstrates superior performance compared to state-of-the-art results.","keywords":"#Analysis, #ECCV\\textgreater10, #Representation\\textgreaterSR, #Vision, /unread, Image Degradation Model, Noisy Image, Overcomplete Representation, Shrinkage Function, Sparse Representation, ⭐⭐⭐⭐","pages":"622–635","bibtex":"@inproceedings{adler_shrinkage_2010,\n\taddress = {Berlin, Heidelberg},\n\tseries = {Lecture {Notes} in {Computer} {Science}},\n\ttitle = {A {Shrinkage} {Learning} {Approach} for {Single} {Image} {Super}-{Resolution} with {Overcomplete} {Representations}},\n\tisbn = {978-3-642-15552-9},\n\tdoi = {10.1007/978-3-642-15552-9_45},\n\tabstract = {We present a novel approach for online shrinkage functions learning in single image super-resolution. The proposed approach leverages the classical Wavelet Shrinkage denoising technique where a set of scalar shrinkage functions is applied to the wavelet coefficients of a noisy image. In the proposed approach, a unique set of learned shrinkage functions is applied to the overcomplete representation coefficients of the interpolated input image. The super-resolution image is reconstructed from the post-shrinkage coefficients. During the learning stage, the low-resolution input image is treated as a reference high-resolution image and a super-resolution reconstruction process is applied to a scaled-down version of it. The shapes of all shrinkage functions are jointly learned by solving a Least Squares optimization problem that minimizes the sum of squared errors between the reference image and its super-resolution approximation. Computer simulations demonstrate superior performance compared to state-of-the-art results.},\n\tlanguage = {en},\n\tbooktitle = {Computer {Vision} – {ECCV} 2010},\n\tpublisher = {Springer},\n\tauthor = {Adler, Amir and Hel-Or, Yacov and Elad, Michael},\n\teditor = {Daniilidis, Kostas and Maragos, Petros and Paragios, Nikos},\n\tyear = {2010},\n\tnote = {TLDR: A novel approach for online shrinkage functions learning in single image super-resolution that leverages the classical Wavelet Shrinkage denoising technique and demonstrates superior performance compared to state-of-the-art results.},\n\tkeywords = {\\#Analysis, \\#ECCV{\\textgreater}10, \\#Representation{\\textgreater}SR, \\#Vision, /unread, Image Degradation Model, Noisy Image, Overcomplete Representation, Shrinkage Function, Sparse Representation, ⭐⭐⭐⭐},\n\tpages = {622--635},\n}\n\n\n\n","author_short":["Adler, A.","Hel-Or, Y.","Elad, M."],"editor_short":["Daniilidis, K.","Maragos, P.","Paragios, N."],"key":"adler_shrinkage_2010","id":"adler_shrinkage_2010","bibbaseid":"adler-helor-elad-ashrinkagelearningapproachforsingleimagesuperresolutionwithovercompleterepresentations-2010","role":"author","urls":{},"keyword":["#Analysis","#ECCV\\textgreater10","#Representation\\textgreaterSR","#Vision","/unread","Image Degradation Model","Noisy Image","Overcomplete Representation","Shrinkage Function","Sparse Representation","⭐⭐⭐⭐"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/zzhenry2012","dataSources":["nZHrFJKyxKKDaWYM8"],"keywords":["#analysis","#eccv\\textgreater10","#representation\\textgreatersr","#vision","/unread","image degradation model","noisy image","overcomplete representation","shrinkage function","sparse representation","⭐⭐⭐⭐"],"search_terms":["shrinkage","learning","approach","single","image","super","resolution","overcomplete","representations","adler","hel-or","elad"],"title":"A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations","year":2010}