Filters








299 Hits in 8.0 sec

Intra-frame deblurring by leveraging inter-frame camera motion

Haichao Zhang, Jianchao Yang
<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;
A video deblurring method is proposed based on two observations: ( ) camera motion within capture of each individual frame leads to motion blur; ( ) camera motion between frames yields inter-frame misalignment  ...  Related Work Single-/Multi-Image Blind Deblurring Blind deblurring techniques using a single image can be classified into maximum a posterior (MAP) estimators with different prior/penalty terms [20, 4  ...  Deblurring results using a single-image-based deblurring method [29] are also presented in Figure 7 for comparison.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7299030">doi:10.1109/cvpr.2015.7299030</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZhangY15.html">dblp:conf/cvpr/ZhangY15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qlbjjxslyjenjngkkygvxgnae4">fatcat:qlbjjxslyjenjngkkygvxgnae4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160824012435/http://www.cv-foundation.org:80/openaccess/content_cvpr_2015/papers/Zhang_Intra-Frame_Deblurring_by_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/d8/7a/d87a26f5a15ce628830e762ea9e58283173f6d1d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7299030"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Non-Uniform Blind Deblurring with a Spatially-Adaptive Sparse Prior [article]

Haichao Zhang, David Wipf
<span title="2013-06-17">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The underlying objective function includes a spatially adaptive penalty which couples the latent sharp image, non-uniform blur operator, and noise level together.  ...  Using ideas from Bayesian inference and convex analysis, this paper derives a non-uniform blind deblurring algorithm with several desirable, yet previously-unexplored attributes.  ...  The deblurred images and estimated kernel maps obtained using the proposed spatially adaptive sparsity (left) and standard spatially non-adaptive sparsity (right) for the Elephant image shown inFigure  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1306.3828v1">arXiv:1306.3828v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wtfk63o2bvd73go3mjodth2dea">fatcat:wtfk63o2bvd73go3mjodth2dea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826062615/https://arxiv.org/pdf/1306.3828v1.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/31/ce/31cecfc4a9e239c631fa3df5f1fa3818394683ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1306.3828v1" 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>

Single-Image Super-Resolution via Adaptive Joint Kernel Regression

Chen Huang, Xiaoqing Ding, Chi Fang
<span title="">2013</span> <i title="British Machine Vision Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6bfo5625nvdfvbgyf7ldi5wmfe" style="color: black;">Procedings of the British Machine Vision Conference 2013</a> </i> &nbsp;
This paper proposes an adaptive joint kernel regression framework for single-image super-resolution (SR).  ...  Combining them into one single regularization term leads to a joint kernel regression scheme that simultaneously exploits both image statistics in a natural manner.  ...  Conclusions This paper introduces an adaptive joint kernel regression framework for single-image superresolution.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.27.101">doi:10.5244/c.27.101</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/bmvc/HuangDF13.html">dblp:conf/bmvc/HuangDF13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hl4vmpc74vew3cnjcphaiw75wm">fatcat:hl4vmpc74vew3cnjcphaiw75wm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180721102118/http://www.bmva.org/bmvc/2013/Papers/paper0101/paper0101.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/49/ad/49ada98161329e6298ae6c8792c26d840dc788b7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.27.101"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Kernel estimation from salient structure for robust motion deblurring

Jinshan Pan, Risheng Liu, Zhixun Su, Xianfeng Gu
<span title="">2013</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lbq64z5tgbddzjqwttcy2pxhsi" style="color: black;">Signal processing. Image communication</a> </i> &nbsp;
Finally, we developed an adaptive weighted spatial prior, for the purpose of preserving sharp edges in latent image restoration.  ...  In this paper, we focus on how to estimate a good kernel estimate from a single blurred image based on the image structure.  ...  It also has strong penalty to these areas which are flat or contain narrow strips as well. Model (4), however, can adaptively obtain the intrinsic image structures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.image.2013.05.001">doi:10.1016/j.image.2013.05.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nlzlcyecfbavxkfcyosq57mzai">fatcat:nlzlcyecfbavxkfcyosq57mzai</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1212.1073/1212.1073.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> File Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.image.2013.05.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

Weisheng Dong, Lei Zhang, Guangming Shi, Xiaolin Wu
<span title="">2011</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;
Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than  ...  As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications.  ...  CONCLUSION We proposed a novel sparse representation-based image deblurring and (single-image) super-resolution method using adaptive sparse domain selection (ASDS) and adaptive regularization (AReg).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2011.2108306">doi:10.1109/tip.2011.2108306</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/21278019">pmid:21278019</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kruc7xhp5be2bgc4ci52wnnk64">fatcat:kruc7xhp5be2bgc4ci52wnnk64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830011155/http://see.xidian.edu.cn/faculty/wsdong/Papers/Journal/ASDS_TIP.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/cf/bccff9a9538751f89fac28f779fca9e11f054491.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2011.2108306"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Model Adaptation for Inverse Problems in Imaging [article]

Davis Gilton, Gregory Ongie, Rebecca Willett
<span title="2021-04-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show these simple model adaptation approaches achieve empirical success in a variety of inverse problems, including deblurring, super-resolution, and undersampled image reconstruction in magnetic resonance  ...  imaging.  ...  For the deblurring task, the unknown blur kernel is parametrized as a 7x7 blur kernel, initialized with the weights used for the ground-truth kernel during the initial stage of training.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00139v2">arXiv:2012.00139v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xk2dp2dfwvdbvmgahgdn6ru37m">fatcat:xk2dp2dfwvdbvmgahgdn6ru37m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201205000213/https://arxiv.org/pdf/2012.00139v1.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/5d/40/5d403a543013cb0f6e2c33758bfe9bab5912dbb4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00139v2" 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>

Image reconstruction with locally adaptive sparsity and nonlocal robust regularization

Weisheng Dong, Guangming Shi, Xin Li, Lei Zhang, Xiaolin Wu
<span title="">2012</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lbq64z5tgbddzjqwttcy2pxhsi" style="color: black;">Signal processing. Image communication</a> </i> &nbsp;
Sparse representation based modeling has been successfully used in many image-related inverse problems such as deblurring, super-resolution and compressive sensing.  ...  along with adaptive learning of PCA-based dictionaries; (2) a nonlocal self-similarity constraint is introduced into the overall cost functional to improve the robustness of the model.  ...  [39] ; deblurred image by [39] ; the deblurred image by Algorithm 2 with blurring kernel estimated using [39] ; close-up views.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.image.2012.09.003">doi:10.1016/j.image.2012.09.003</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rhewpllaybfo3ileiqt5qw776u">fatcat:rhewpllaybfo3ileiqt5qw776u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830011146/http://see.xidian.edu.cn/faculty/wsdong/Papers/Journal/SP_IC_Dong.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/cb/b9/cbb9c6b2d3b854fcf60b71a234ca8060b5cc8c25.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.image.2012.09.003"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Blind deconvolution using a normalized sparsity measure

Dilip Krishnan, Terence Tay, Rob Fergus
<span title="">2011</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">CVPR 2011</a> </i> &nbsp;
This allows a very simple cost formulation to be used for the blind deconvolution model, obviating the need for additional methods. Due to its simplicity the algorithm is fast and very robust.  ...  Bayesian methods, adaptive cost functions, alpha-matte extraction and edge localization).  ...  These include: marginalization over all possible images [4, 15, 17] ; dynamic adaptation of the cost function [22] ; alpha-matt extraction [10] ; re-weighting of the image edges [3] ; determination  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2011.5995521">doi:10.1109/cvpr.2011.5995521</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/KrishnanTF11.html">dblp:conf/cvpr/KrishnanTF11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lmj6qvv62bavnc2unsxhce4k2q">fatcat:lmj6qvv62bavnc2unsxhce4k2q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150813061332/http://cs.nyu.edu/%7Edilip/wordpress/papers/priors_cvpr11.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/30/12/30122448f269e453c800331fac5421f36be7697a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2011.5995521"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.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;
[9] use the weighted regularization strategy in non-blind deconvolution stage and also obtain impressive fine details for some images. However, [9] notes that it is less robust to outliers.  ...  Among the edge extraction methods, adaptive weighted gradient model [9, 11] is especially appropriate to restore salient edges.  ...  [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>

Kernel Optimization for Blind Motion Deblurring with Image Edge Prior

Jing Wang, Ke Lu, Qian Wang, Jie Jia
<span title="">2012</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;
For kernel optimization, an edge mask is used as an image prior to improve kernel update, then an edge selection mask is adopted to improve image update.  ...  Image motion deblurring with unknown blur kernel is an ill-posed problem. This paper proposes a blind motion deblurring approach that solves blur kernel and the latent image robustly.  ...  In this paper, we mainly focus on the single-image-based motion deblurring. To address such challenging problem, various theories and methods have been proposed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2012/639824">doi:10.1155/2012/639824</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cjntfldhmrdhtekwbdl5zbbu2a">fatcat:cjntfldhmrdhtekwbdl5zbbu2a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190505034735/http://downloads.hindawi.com/journals/mpe/2012/639824.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/46/bd/46bd618aef9167c40ea63323f30b5ddd79480505.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2012/639824"> <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>

Blind Image Deconvolution using Deep Generative Priors [article]

Muhammad Asim, Fahad Shamshad, Ali Ahmed
<span title="2019-02-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors.  ...  Interestingly, our experiments show that even an untrained structured (convolutional) generative networks acts as an image prior in the image deblurring context allowing us to extend our results to more  ...  The weights of the untrained network are initialized using a single blurred image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.04073v4">arXiv:1802.04073v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cuj2bsznhvfkzdtf4q6o5dmepq">fatcat:cuj2bsznhvfkzdtf4q6o5dmepq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191020120156/https://arxiv.org/pdf/1802.04073v4.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/d0/59/d0590c560c6f105746ee546dc47410fb5758a224.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.04073v4" 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>

Blur Removal via Blurred-Noisy Image Pair [article]

Chunzhi Gu, Xuequan Lu, Ying He, Chao Zhang
<span title="2020-11-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a novel image deblurring method that does not need to estimate blur kernels.  ...  We eventually add a detail layer to the deblurred image for refinement.  ...  CONCLUSION We proposed a novel, robust image deblurring method with the use of a pair of blurred/noisy images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.10667v4">arXiv:1903.10667v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c2u7ezk3krdpth3fhxxi3ke46m">fatcat:c2u7ezk3krdpth3fhxxi3ke46m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201118004017/https://arxiv.org/pdf/1903.10667v4.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/44/a5/44a5d2c46a8fb1490ec4ec773c0e1d7a05d82259.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.10667v4" 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>

End-to-End Learning for Image Burst Deblurring [article]

Patrick Wieschollek, Bernhard Schölkopf, Hendrik P.A. Lensch, Michael Hirsch
<span title="2016-09-06">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The discriminative approach adopts and combines two recent techniques for image deblurring into a single neural network architecture.  ...  In order to make full use of the information contained in all images in one burst, the proposed network embeds smaller networks, which explicitly allow the model to transfer information between images  ...  The outputs are recomposed to yield an initial estimate of the latent sharp image, which is then used together with the blurry input image for the estimation of a single invariant blur kernel.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1607.04433v2">arXiv:1607.04433v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jffoi2ncyrcsregj5f3rhyef3q">fatcat:jffoi2ncyrcsregj5f3rhyef3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826213454/https://arxiv.org/pdf/1607.04433v2.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/e0/6e/e06ea623ad67154f98ab85e9841a0262bcd766a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1607.04433v2" 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>

Dataset and Network Structure: Towards Frames Selection for Fast Video Deblurring

Abdelwahed Nahli, Shan Cao, Jia Zhiwei, Runze Ma, Shugong Xu
<span title="">2021</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;
In this work, we measure the image quality using the RGB channels to put more weight on the color as well as the luminance. D.  ...  They are successful in image deblurring and synthesis, respectively. [27] make use of dilated convolution layers with increasing rates, which approximates increasing kernel sizes. C.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3074199">doi:10.1109/access.2021.3074199</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jcqk6tkydnbkhcn6opgnpkjzja">fatcat:jcqk6tkydnbkhcn6opgnpkjzja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210422033015/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09408635.pdf?tp=&amp;arnumber=9408635&amp;isnumber=6514899&amp;ref=" 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/52/fc5244c233be1c8901e32dd15e9a4d8aab3fe60a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3074199"> <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>

Binarization Driven Blind Deconvolution for Document Image Restoration [chapter]

Thomas Köhler, Andreas Maier, Vincent Christlein
<span title="">2015</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;
Blind deconvolution is a common method for restoration of blurred text images, while binarization is employed to analyze and interpret the text semantics.  ...  We also demonstrate the application of our method for the restoration and binarization of historic document images, where it improves the visual recognition of handwritten text.  ...  Then, we adjusted the regularization weights of all compared deconvolution methods on one single training image taken from our simulated data by optimizing the PSNR of the deblurred image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-24947-6_8">doi:10.1007/978-3-319-24947-6_8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m3fbrxk2wnhtxlwcq567uymz2q">fatcat:m3fbrxk2wnhtxlwcq567uymz2q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829050358/https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Koehler15-BDB.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/78/a0/78a0d4d23c5fb294690054c483c0a2c7d0446887.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-24947-6_8"> <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 299 results