Filters








251 Hits in 4.6 sec

Hyper-Laplacian Regularized Non-local Lowrank Prior for Blind Image Deblurring

Xiaole Chen, Ruifeng Yang, Chenxia Guo, Shuangchao Ge, Zhihong Wu, Xiben Liu
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Then we use the hyper-Laplace prior to model the structure information of non-local similar patches, and propose a hyper-Laplacian regularized non-local low-rank matrix approximation model for blind image  ...  HYPER-LAPLACIAN REGULARIZED NON-LOCAL LRMA MODEL Despite the great success of LRMA model in image restoration, most methods enforce sparsity constraints only across the spatial domain which cannot well  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3010540">doi:10.1109/access.2020.3010540</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/23k43556lba6xmhjki3ndhzh3i">fatcat:23k43556lba6xmhjki3ndhzh3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107095853/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09144594.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/11/d6/11d6f23373c66a077b51542701f0744845a005ab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3010540"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Image deconvolution using multigrid natural image prior and its applications

Tingbo Hou, Sen Wang, Hong Qin, Rodney L. Miller
<span title="">2010</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2010 IEEE International Conference on Image Processing</a> </i> &nbsp;
In this paper, we present a multigrid natural image prior for image deconvolution that enhances its robustness against noise, and furnish three applications of image deconvolution using this prior: deblurring  ...  The natural image prior has been shown as a powerful tool for image deblurring in recent work, while its performance against noise and various applications have not been thoroughly studied.  ...  While people from different fields have different focuses on this problem, we are mainly interested by the recent progress in image deblurring using the natural image prior [1, 2, 3, 4] , which refers  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2010.5651083">doi:10.1109/icip.2010.5651083</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/HouWQM10.html">dblp:conf/icip/HouWQM10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4z5j6urdqffuva3vllvckmzdzq">fatcat:4z5j6urdqffuva3vllvckmzdzq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706111416/http://www3.cs.stonybrook.edu/~qin/research/2010-icip-image-deconvolution.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/cf/4fcfcece1b39de39179ce0b7b8cd11f0948aa617.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2010.5651083"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Robust Alternating Direction Method for Constrained Hybrid Variational Deblurring Model [article]

Ryan Wen Liu, Tian Xu
<span title="2013-10-02">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, a box constraint is imposed on the proposed model to guarantee high deblurring performance.  ...  The developed constrained hybrid variational model could achieve a good balance between preserving image details and alleviating ringing artifacts.  ...  From a statistical point of view, the second-order derivatives also follow the hyper-Laplacian distribution.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1309.0123v2">arXiv:1309.0123v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d2mnnergnbeorda55ahtgaglve">fatcat:d2mnnergnbeorda55ahtgaglve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015023539/https://arxiv.org/pdf/1309.0123v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3c/01/3c017e164398e24f610cd873c1e7f38f891ef13a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1309.0123v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Graph-Based Blind Image Deblurring From a Single Photograph

Yuanchao Bai, Gene Cheung, Xianming Liu, Wen Gao
<span title="">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem.  ...  Specifically for Gaussian blur, we propose a further speedup strategy for blind Gaussian deblurring using accelerated graph spectral filtering.  ...  Afterwards, we use the classic hyper-Laplacian based non-blind deblurring algorithm [17] to restore the latent sharp image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2874290">doi:10.1109/tip.2018.2874290</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30307861">pmid:30307861</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x4xiimoevzbvlbi5ylpcnjonxa">fatcat:x4xiimoevzbvlbi5ylpcnjonxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914141016/https://arxiv.org/pdf/1802.07929v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/67/8a/678a9eaac65726bb13e65c16cacb528c6fd95b4c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2018.2874290"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Image deblurring and denoising using color priors

N. Joshi, C.L. Zitnick, R. Szeliski, D.J. Kriegman
<span title="">2009</span> <i title="IEEE"> 2009 IEEE Conference on Computer Vision and Pattern Recognition </i> &nbsp;
Our algorithm uses local color statistics derived from the image as a constraint in a unified framework that can be used for deblurring, denoising, and upsampling.  ...  We present a novel image deconvolution algorithm that deblurs and denoises an image given a known shift-invariant blur kernel.  ...  s [12] work, we minimize the hyper-Laplacian α prior using a re-weighting function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2009.5206802">doi:10.1109/cvprw.2009.5206802</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/chfd47rnh5cl5iarhk2eyodugm">fatcat:chfd47rnh5cl5iarhk2eyodugm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100626022223/http://vision.ucsd.edu/kriegman-grp/papers/cvpr09a.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/85/f0/85f03bc66c06f705c9b9bd4ed0c6a0023421f371.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2009.5206802"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Image deblurring and denoising using color priors

Neel Joshi, C. Lawrence Zitnick, Richard Szeliski, David J. Kriegman
<span title="">2009</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2009 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
Our algorithm uses local color statistics derived from the image as a constraint in a unified framework that can be used for deblurring, denoising, and upsampling.  ...  We present a novel image deconvolution algorithm that deblurs and denoises an image given a known shift-invariant blur kernel.  ...  s [12] work, we minimize the hyper-Laplacian α prior using a re-weighting function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2009.5206802">doi:10.1109/cvpr.2009.5206802</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/JoshiZSK09.html">dblp:conf/cvpr/JoshiZSK09</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gq7swvr5yrav3gftthf73honwi">fatcat:gq7swvr5yrav3gftthf73honwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100626022223/http://vision.ucsd.edu/kriegman-grp/papers/cvpr09a.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/85/f0/85f03bc66c06f705c9b9bd4ed0c6a0023421f371.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2009.5206802"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Fast high-quality non-blind deconvolution using sparse adaptive priors

Horacio E. Fortunato, Manuel M. Oliveira
<span title="2014-05-13">2014</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yx6ragzaojavld2pw4coglzb2e" style="color: black;">The Visual Computer</a> </i> &nbsp;
We model the image-prior deconvolution problem as a linear system, which is solved in the frequency domain. Our approach's clean formulation lends to a simple and efficient implementation.  ...  We demonstrate its effectiveness by performing an extensive comparison with existing non-blind deconvolution methods, and by using it to deblur actual photographs degraded by camera shake or motion.  ...  The images used for technique comparisons are from the Kodak Lossless True Color Image Suite -PhotoCD PCD0992 [15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s00371-014-0966-x">doi:10.1007/s00371-014-0966-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m2ifhzva75h7lllgizwols7t4m">fatcat:m2ifhzva75h7lllgizwols7t4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810170649/http://www.inf.ufrgs.br/%7Eoliveira/pubs_files/FD/Fortunato_Oliveira_Fast_High_Quality_non-Blind_Deconvolution_small.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b4/72/b4729432b23842ff6b1b126572f8fa17aca14758.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s00371-014-0966-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

ABLUR: An FPGA-based adaptive deblurring core for real-time applications

Giuseppe Airo Farulla, Marco Indaco, Paolo Prinetto, Daniele Rolfo, Pascal Trotta
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/74wwkahd4bbfnlle2od7myqj4u" style="color: black;">2014 NASA/ESA Conference on Adaptive Hardware and Systems (AHS)</a> </i> &nbsp;
The Dynamic Partial Reconfiguration (DPR) feature of modern FPGAs is exploited to enable self-adaptation of the deblurring algorithm parameters to the input images characteristics.  ...  In such cases, weight of equipments is of absolute importance, and no extra hardware can be used.  ...  An interesting single-image deblurring approach based on Hyper-Laplacian priors is presented in [18] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ahs.2014.6880165">doi:10.1109/ahs.2014.6880165</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ahs/FarullaIPRT14.html">dblp:conf/ahs/FarullaIPRT14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rlqvipek6zdftl2uocdcmwlqhe">fatcat:rlqvipek6zdftl2uocdcmwlqhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724042850/https://iris.polito.it/retrieve/handle/11583/2572144/63672/2014_AHS_ABLUR_AuthorVersion.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/20/4e/204ef609a3aab8bd94ba78d9c9cfe402f5e1aef0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ahs.2014.6880165"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A General Framework for Regularized, Similarity-Based Image Restoration

Amin Kheradmand, Peyman Milanfar
<span title="">2014</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
This procedure improves the performance of the algorithm for image deblurring, where we do not have access to a good initial estimate of the underlying image.  ...  The normalizing coefficients used in the definition of the Laplacian and associated regularization term are obtained using fast symmetry preserving matrix balancing.  ...  of hyper-Laplacian algorithm Fig. 15 . 15 Real motion deblurring example: (a) input blurred noisy image, (b) Output of hyper-Laplacian algorithm using the traditional normalized Laplacian I −W D =  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2014.2362059">doi:10.1109/tip.2014.2362059</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/25312932">pmid:25312932</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6algpogo3rfllpj2ukutnzul64">fatcat:6algpogo3rfllpj2ukutnzul64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160429172332/https://users.soe.ucsc.edu/~milanfar/publications/journal/TIP_Amin_Final.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bc/99/bc99da9ea8b6e3b1efabbabc7d72c4ddba7f6776.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2014.2362059"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

An Improved Adaptive Deconvolution Algorithm for Single Image Deblurring

Hsin-Che Tsai, Jiunn-Lin Wu
<span title="">2014</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wpareqynwbgqdfodcyhh36aqaq" style="color: black;">Mathematical Problems in Engineering</a> </i> &nbsp;
Shift-invariant motion blur can be modeled as a convolution of the true latent image and a point spread function (PSF) with additive noise.  ...  To suppress undesirable artifacts, regularization based methods have been proposed using natural image priors to overcome the ill-posedness of deconvolution problem.  ...  These distributions are well modeled by a hyper-Laplacian prior and have proven effective priors for deblurring problem.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2014/658915">doi:10.1155/2014/658915</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6klfb5354rbsrlvpcgtmjdgfwa">fatcat:6klfb5354rbsrlvpcgtmjdgfwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170819194234/http://downloads.hindawi.com/journals/mpe/2014/658915.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/70/e270d27a332ddf7e6990921df3210dea508e1100.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2014/658915"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Natural Image Deblurring Based on Ringing Artifacts Removal via Knowledge-driven Gradient Distribution Priors

Hongtian Zhao, Hua Yang, Hang Su, Shibao Zheng
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Prominent examples include Laplacian function [18] , Hyper-Laplacian priors [3] , Gaussian distribution [2] , and their fitting results are shown in Fig. 3 (b) .  ...  The core task and vital part of image deblurring are formulating appropriate priors with strong discriminatory ability, developing typical image models along with effective and robust optimization algorithms  ...  [31] (h) Ours FIGURE 15: Qualitative evaluations on the real-life blurry images [6, 9] and sword image captured by us. (a) Blurred input (b) Krishnan et al. [5] (c) Pan et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3007972">doi:10.1109/access.2020.3007972</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fbo3k7sdyrafbilkjl3zu52ele">fatcat:fbo3k7sdyrafbilkjl3zu52ele</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108122942/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09136686.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/42/50/42504965435b136371edbdc56a39687879830792.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3007972"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Learning Data Terms for Non-blind Deblurring [chapter]

Jiangxin Dong, Jinshan Pan, Deqing Sun, Zhixun Su, Ming-Hsuan Yang
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Existing deblurring methods mainly focus on developing effective image priors and assume that blurred images contain insignificant amounts of noise.  ...  However, state-of-the-art deblurring methods do not perform well on real-world images degraded with significant noise or outliers.  ...  To understand the role of the data term for image deblurring, we use the standard hyper-Laplacian prior for the latent image [7, 8] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01252-6_46">doi:10.1007/978-3-030-01252-6_46</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xkj62eanhjbcjp5zythy4cxsi4">fatcat:xkj62eanhjbcjp5zythy4cxsi4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819005201/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Jiangxin_Dong_Learning_Data_Terms_ECCV_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/4a/954a44fca304778f345c8637b36133ce1597dedd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01252-6_46"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Discriminative learning of iteration-wise priors for blind deconvolution

Wangmeng Zuo, Dongwei Ren, Shuhang Gu, Liang Lin, Lei Zhang
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
The family of hyper-Laplacian (Pr(d) ∝ e − d p p /λ ) is adopted for modeling iteration-wise priors of image gradients, where each iteration has its own model parameters {λ (t) , p (t) }.  ...  To avoid heavy parameter tuning, all iterationwise model parameters can be learned using our principled discriminative learning model from a training set, and can be directly applied to other dataset and  ...  In this work, hyper-Laplacian is adopted for modeling image gradients which is limited in modeling patch-level structures in images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7298943">doi:10.1109/cvpr.2015.7298943</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZuoRGLZ15.html">dblp:conf/cvpr/ZuoRGLZ15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ffiqrptx2je3bcus4vmnsboqfm">fatcat:ffiqrptx2je3bcus4vmnsboqfm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160128221224/http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zuo_Discriminative_Learning_of_2015_CVPR_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/56/fc56666dcf557c62559ee52413aaac928924ebcd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7298943"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Deblurring Turbulent Images via Maximizing L1 Regularization

Lizhen Duan, Shuhan Sun, Jianlin Zhang, Zhiyong Xu
<span title="2021-08-03">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nzoj5rayr5hutlurimhzyjlory" style="color: black;">Symmetry</a> </i> &nbsp;
Atmospheric turbulence significantly degrades image quality. A blind image deblurring algorithm is needed, and a favorable image prior is the key to solving this problem.  ...  Then, a novel soft suppression strategy is designed for the deblurring algorithm to inhibit artifacts. A coarse-to-fine scheme and a non-blind algorithm are also constructed.  ...  To encourage gradients sparsity, the Laplacian and hyper-Laplacian functions [3] [4] [5] [6] are used as image priors. Then, Levin et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym13081414">doi:10.3390/sym13081414</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/peooua72yzegfhb3qkbqevggbm">fatcat:peooua72yzegfhb3qkbqevggbm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210810000130/https://res.mdpi.com/d_attachment/symmetry/symmetry-13-01414/article_deploy/symmetry-13-01414.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b8/8d/b88da38aa6f437575bd33746e4cf4b89ea2237eb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym13081414"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Nonlocal Spectral Prior Model for Low-Level Vision [chapter]

Shenlong Wang, Lei Zhang, Yan Liang
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We consequently apply the NSP model to typical image restoration tasks, including denoising, superresolution and deblurring, and the experimental results demonstrated the highly competitive performance  ...  A novel image prior model, namely nonlocal spectral prior (NSP) model, is then proposed to characterize the singular values of nonlocal similar patches.  ...  We use two state-of-the-art methods for motion deblurring as our competing algorithms: the hyper-Laplacian proposed by Krishnan et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-37431-9_18">doi:10.1007/978-3-642-37431-9_18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6zuio5ik3nfdfk7ewvuo2mzhxe">fatcat:6zuio5ik3nfdfk7ewvuo2mzhxe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160519084911/http://www4.comp.polyu.edu.hk:80/~cslzhang/paper/conf/ACCV12_NSP.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/36/69/366954363c99333612013ca283ff9640229a0f41.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-37431-9_18"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 251 results