Filters








82 Hits in 2.5 sec

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks [article]

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas
<span title="2018-04-03">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss .  ...  The model, code and the dataset are available at https://github.com/KupynOrest/DeblurGAN  ...  Conclusion We described a kernel-free blind motion deblurring learning approach and introduced DeblurGAN which is a Conditional Adversarial Network that is optimized using a multi-component loss function  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.07064v4">arXiv:1711.07064v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzcsivvhyjcn5jhsqswablshm4">fatcat:nzcsivvhyjcn5jhsqswablshm4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022001536/https://arxiv.org/pdf/1711.07064v4.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/ec/93/ec93e6a961a1524b0f153f470ea765c048c0c637.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.07064v4" 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>

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
We present DeblurGAN, an end-to-end learned method for motion deblurring. The learning is based on a conditional GAN and the content loss .  ...  The method is 5 times faster than the closest competitor -Deep-Deblur [25] .  ...  Conclusion We described a kernel-free blind motion deblurring learning approach and introduced DeblurGAN which is a Conditional Adversarial Network that is optimized using a multi-component loss function  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00854">doi:10.1109/cvpr.2018.00854</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/KupynBMMM18.html">dblp:conf/cvpr/KupynBMMM18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ewapgi3ti5cm7nhszp2zkemoqu">fatcat:ewapgi3ti5cm7nhszp2zkemoqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819012215/http://openaccess.thecvf.com:80/content_cvpr_2018/papers/Kupyn_DeblurGAN_Blind_Motion_CVPR_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/f5/e7/f5e7eae1fc1f26546eb1b4cf33cd85585653c037.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00854"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better [article]

Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
<span title="2019-08-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility  ...  DeblurGAN-v2 is based on a relativistic conditional GAN with a double-scale discriminator.  ...  Introduction This paper focuses on the challenging setting of singleimage blind motion deblurring.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.03826v1">arXiv:1908.03826v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6nlzgctwd5a5zf7kew72y2upsa">fatcat:6nlzgctwd5a5zf7kew72y2upsa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825213056/https://arxiv.org/pdf/1908.03826v1.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/81/c1/81c1dc00b32d12edfab00656593f5db56cfa79e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.03826v1" 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>

Restoration of Motion Blurred Image by Modified DeblurGAN for Enhancing the Accuracies of Finger-Vein Recognition

Jiho Choi, Jin-Seong Hong, Muhammad Owais, Seung-Gu Kim, Kang-Ryoung Park
<span title="2021-07-06">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
network (modified DeblurGAN).  ...  To address this problem, this study proposes a new method for improving the finger-vein recognition performance by restoring motion blurred finger-vein images using a modified deblur generative adversarial  ...  A deblurring task can be generally divided into blind and non-blind deblurring.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21144635">doi:10.3390/s21144635</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/urtojl7aujfg3lmcxl4ax5poya">fatcat:urtojl7aujfg3lmcxl4ax5poya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210713115444/https://res.mdpi.com/d_attachment/sensors/sensors-21-04635/article_deploy/sensors-21-04635-v2.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/d1/c9/d1c9d62c53e7469f1124ef9531caec45cc050aae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21144635"> <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>

SL-CycleGAN: Blind Motion Deblurring in Cycles using Sparse Learning [article]

Ali Syed Saqlain, Li-Yun Wang, Fang Fang
<span title="2021-11-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce an end-to-end generative adversarial network (GAN) based on sparse learning for single image blind motion deblurring, which we called SL-CycleGAN.  ...  For the first time in blind motion deblurring, we propose a sparse ResNet-block as a combination of sparse convolution layers and a trainable spatial pooler k-winner based on HTM (Hierarchical Temporal  ...  [35] proposed a conditional GAN-framework (DeblurGAN) for single image blind motion deblurring.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.04026v1">arXiv:2111.04026v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/phvtm3b53rhdppsnewmntf6vme">fatcat:phvtm3b53rhdppsnewmntf6vme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211113035544/https://arxiv.org/pdf/2111.04026v1.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/62/18/62182d71c54e509289d262c5d2b57ba0b6d26dea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.04026v1" 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>

FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks [article]

Jatin Kumar and Indra Deep Mastan and Shanmuganathan Raman
<span title="2021-12-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present a Fast Motion Deblurring-Conditional Generative Adversarial Network (FMD-cGAN) that helps in blind motion deblurring of a single image.  ...  The resulting compressed Deblurring cGAN faster than its closest competitors and even qualitative and quantitative results outperform various recently proposed state-of-the-art blind motion deblurring  ...  FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks 3 Non-blind deblurring is an ill-posed problem.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.15438v2">arXiv:2111.15438v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ouphc37dp5avnhxrrvgx47dbge">fatcat:ouphc37dp5avnhxrrvgx47dbge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211211090532/https://arxiv.org/pdf/2111.15438v2.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/76/bc/76bc59dfb01f45345fddf80f726fdd87d499ca68.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.15438v2" 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>

GAN-based image deblurring using DCT loss with customized datasets

Hiroki Tomosada, Takahiro Kudo, Takanori Fujisawa, Masaaki Ikehara
<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;
Recently, Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) based algorithms have been proposed for image deblurring.  ...  In this paper, we propose a high quality image deblurring method that uses discrete cosine transform (DCT) and requires less computational complexity.  ...  We optimize our network by the same training conditions as DeblurGAN, SRN, and DeblurGANv2. The patch size and the mini-batch size is set to 256 × 256 and 8, respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3116194">doi:10.1109/access.2021.3116194</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ck2y2svfqzax7newy3nmg7zvtu">fatcat:ck2y2svfqzax7newy3nmg7zvtu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210930221405/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09551883.pdf?tp=&amp;arnumber=9551883&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/98/c1/98c1110a7f60e7fc0466e078a345840b7d114b01.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3116194"> <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>

Blind Motion Deblurring through SinGAN Architecture [article]

Harshil Jain, Rohit Patil, Indra Deep Mastan, Shanmuganathan Raman
<span title="2020-11-07">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we focus on blind motion deblurring through SinGAN architecture.  ...  Blind motion deblurring involves reconstructing a sharp image from an observation that is blurry. It is a problem that is ill-posed and lies in the categories of image restoration problems.  ...  Conclusion We show how to perform training data-independent blind motion deblurring using SinGAN.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.03705v1">arXiv:2011.03705v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tbeaiakd5vd3bar3556qnrba5a">fatcat:tbeaiakd5vd3bar3556qnrba5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201111081746/https://arxiv.org/pdf/2011.03705v1.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/c8/c3/c8c3cd2488491ba6e2b27013b4a48a5af525dcb4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.03705v1" 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>

Deep Image Deblurring: A Survey [article]

Kaihao Zhang, Wenqi Ren, Wenhan Luo, Wei-Sheng Lai, Bjorn Stenger, Ming-Hsuan Yang, Hongdong Li
<span title="2022-01-26">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Next we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison.  ...  Recent advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed.  ...  [57] proposed DeblurGAN, an end-to-end conditional GAN for motion deblurring.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10700v1">arXiv:2201.10700v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z77ogbieirf23brn73375dlht4">fatcat:z77ogbieirf23brn73375dlht4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220129101113/https://arxiv.org/pdf/2201.10700v1.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/ab/cbab6ac238ceceddf8bd87f1bc3338e9e19ffe43.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10700v1" 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 Motion Deblurring Based on Deep Residual Shrinkage and Generative Adversarial Networks

Wenbo Jiang, Anshun Liu, Bai Yuan Ding
<span title="2022-01-21">2022</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3wwzxqpotbc73bzpemzybzg7ee" style="color: black;">Computational Intelligence and Neuroscience</a> </i> &nbsp;
A network structure (DRSN-GAN) is proposed for image motion deblurring that combines a deep residual shrinkage network (DRSN) with a generative adversarial network (GAN) to address the issues of poor noise  ...  Finally, deblurring performance was verified using the GoPro, Köhler, and Lai datasets.  ...  Nine deep residual shrinkage networks were used as the GAN generator module. Prior studies have used DeblurGAN for image motion deblurring, combining a residual network and a GAN.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/5605846">doi:10.1155/2022/5605846</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35096042">pmid:35096042</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8799329/">pmcid:PMC8799329</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uz3sfce52bdgfenqfrmda3syvu">fatcat:uz3sfce52bdgfenqfrmda3syvu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220124162235/https://downloads.hindawi.com/journals/cin/2022/5605846.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/30/46/30467200668ade1b649b05c1cae4377868d5bfaa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/5605846"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8799329" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Blur-Attention: A boosting mechanism for non-uniform blurred image restoration [article]

Xiaoguang Li, Feifan Yang, Kin Man Lam, Li Zhuo, Jiafeng Li
<span title="2020-08-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
By introducing the blur-attention network into a conditional generation adversarial framework, we propose an end-to-end blind motion deblurring method, namely Blur-Attention-GAN (BAG), for a single image  ...  We design a multi-level residual connection structure to connect multiple blur-attention modules to form a blur-attention network.  ...  Blind motion deblurring is an ill-posed inverse problem with non-uniform blur kernels, which is a fundamental challenging problem in computer vision.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.08526v1">arXiv:2008.08526v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jprdumvclvbk5bsgw6ydi5dzrm">fatcat:jprdumvclvbk5bsgw6ydi5dzrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828025814/https://arxiv.org/pdf/2008.08526v1.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/75/1d/751d11d4fec5238d0b5cddaa20267efe4a46956e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.08526v1" 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>

SlimDeblurGAN-Based Motion Deblurring and Marker Detection for Autonomous Drone Landing

Noi Quang Truong, Young Won Lee, Muhammad Owais, Dat Tien Nguyen, Ganbayar Batchuluun, Tuyen Danh Pham, Kang Ryoung Park
<span title="2020-07-14">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
slimmed version of deblur generative adversarial network (DeblurGAN) model and a You only look once version 2 (YOLOv2) detector, respectively, and (2) considering the balance between the processing time  ...  However, no study was reported to address non-uniform motion-blurred input images, and most of the previous handcrafted and deep learning-based methods failed to operate with these challenging inputs.  ...  Blind Motion Deblurring by DeblurGAN The family of conditional generative adversarial network (cGAN) [24] was successfully applied in some image translation applications such as super-resolution [25  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20143918">doi:10.3390/s20143918</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32674485">pmid:32674485</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7411990/">pmcid:PMC7411990</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2fufrmotbvfznbx2ezsrxbo22u">fatcat:2fufrmotbvfznbx2ezsrxbo22u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200815234644/https://res.mdpi.com/d_attachment/sensors/sensors-20-03918/article_deploy/sensors-20-03918-v2.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/c6/1b/c61bb00d88fe3a37aa380e19b83e578d8a88b797.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20143918"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7411990" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Deep Motion Blur Removal Using Noisy/Blurry Image Pairs [article]

Shuang Zhang, Ada Zhen, Robert L. Stevenson
<span title="2019-11-25">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recent progress in deep neural networks suggests that kernel free single image deblurring can be efficiently performed, but questions about deblurring performance persist.  ...  To boost the training, gradient loss, adversarial loss and spectral normalization are leveraged.  ...  The development of Conditional Generative Adversarial Nets (CGAN) inspired another type of deep deblurring network called DeblurGAN [2] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.08541v2">arXiv:1911.08541v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/untm7ndhn5ar3bui3hi45jyh5i">fatcat:untm7ndhn5ar3bui3hi45jyh5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827171232/https://arxiv.org/pdf/1911.08541v2.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/a2/e1/a2e1bf0aadd18eb4941fefda626681383841e7a6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.08541v2" 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>

Generative Adversarial Network Based on Multi-feature Fusion Strategy for Motion Image Deblurring

Zhou-xiang Jin Zhou-xiang Jin, Hao Qin Zhou-xiang Jin
<span title="">2022</span> <i title="Angle Publishing Co., Ltd."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/afzxuc375rf6vfgm26hw6lju6u" style="color: black;">Diànnǎo xuékān</a> </i> &nbsp;
In this paper, we propose a new generative adversarial network based on multi-feature fusion strategy for motion image deblurring.  ...  Image deblurring can be divided into two categories: one is the non-blind image deblurring with known fuzzy kernel, and the other is the blind image deblurring with unknown fuzzy kernel.  ...  ., [8] used conditional adversarial networks combined with perceptual loss to perform blind motion deblurring.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.53106/199115992022023301004">doi:10.53106/199115992022023301004</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qprx2szja5dtfjlt67mljqxuc4">fatcat:qprx2szja5dtfjlt67mljqxuc4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220430220919/http://www.csroc.org.tw/journal/JOC33-1/JOC3301-04.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/ec/67/ec673cde9aa21fd072a072fcc6a8477d8d4c7265.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.53106/199115992022023301004"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Gyroscope-Aided Motion Deblurring with Deep Networks [article]

Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä
<span title="2018-11-23">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).  ...  To train our network, we also introduce a novel way of generating realistic training data using the gyroscope.  ...  We compare the proposed approaches against DeblurGAN [12] and Mustaniemi et al. [14] . DeblurGAN is a blind deblurring method based on the conditional generative adversarial networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.00986v2">arXiv:1810.00986v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xjgylv25dfhizi52ieyd265dme">fatcat:xjgylv25dfhizi52ieyd265dme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001063513/https://arxiv.org/pdf/1810.00986v1.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/99/ad/99addb1a85b1cfd8c22eca439bc1954e72254753.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.00986v2" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 82 results