Filters








2,199 Hits in 3.7 sec

A Two-stage Network for Image Deblurring

Ze Pan, Qunbo Lv, Zheng Tan
<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;
FIGURE 2 . 2 Network architecture in one scale. Our two-stage deblurring network consists of a data fidelity network and a prior network.  ...  TWO-STAGE DEBLURRING PROCESS Inspired by the success of the prior term in the traditional objective function, we propose a two-stage processing strategy for the learning-based methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3082211">doi:10.1109/access.2021.3082211</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bsb4dxu2bbcplfbq5uadfxu2uq">fatcat:bsb4dxu2bbcplfbq5uadfxu2uq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210530214435/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09439812.pdf?tp=&amp;arnumber=9439812&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/ec/a6/eca69f0c760b754f356a8883c058345907f48d95.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3082211"> <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>

RefocusGAN: Scene Refocusing Using a Single Image [chapter]

Parikshit Sakurikar, Ishit Mehta, Vineeth N. Balasubramanian, P. J. Narayanan
<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;
We train conditional adversarial networks for deblurring and refocusing using wide-aperture images created from light-fields.  ...  By appropriately conditioning our networks with a focus measure, an in-focus image and a refocus control parameter δ, we are able to achieve generic free-form refocusing over a single image.  ...  Conclusion We present a two-stage approach for comprehensive scene refocusing over a single-image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01225-0_31">doi:10.1007/978-3-030-01225-0_31</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jvnuvfbtuzaflih2thamn3xnqi">fatcat:jvnuvfbtuzaflih2thamn3xnqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819021359/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Parikshit_Sakurikar_Single_Image_Scene_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/7e/c3/7ec3e0628df7dec136128939166644c4f2ec67ec.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01225-0_31"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks [article]

Rajeev Yasarla
<span title="2020-04-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring.  ...  Pixel-wise semantic labels are obtained using a segmentation network.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13106v2">arXiv:1907.13106v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2f6cp2tfdbfnnnxrpg7zj5gy4m">fatcat:2f6cp2tfdbfnnnxrpg7zj5gy4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904123634/https://arxiv.org/pdf/1907.13106v2.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/28/17/28178b13e553ad20f0e43d1cee62a6f503665289.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13106v2" 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>

World From Blur

Jiayan Qiu, Xinchao Wang, Stephen J. Maybank, Dacheng Tao
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
To this end, we train a deep network that jointly predicts the motion trajectory, the deblurred image, and the depth one, all of which in turn form a collaborative and self-supervised cycle that supervise  ...  Unlike prior methods that focus on producing a deblurred image, we propose to estimate and take advantage of the hidden message of a blurred image, the relative motion trajectory, to restore the 3D scene  ...  We compare the performances of the two networks pre-trained on clean images (Pre-Eigen's/Ours on Clean), the performances of the two networks trained using outputs of the deblur network (Pre-Eigen's/Ours  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00869">doi:10.1109/cvpr.2019.00869</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/QiuWMT19.html">dblp:conf/cvpr/QiuWMT19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lfvks6shundlxdxe5kdpmsmjv4">fatcat:lfvks6shundlxdxe5kdpmsmjv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819034119/http://openaccess.thecvf.com:80/content_CVPR_2019/papers/Qiu_World_From_Blur_CVPR_2019_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/dd/e4/dde47480f7efd36903d3e554256f6f1d185d6415.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00869"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Event-Based Fusion for Motion Deblurring with Cross-modal Attention [article]

Lei Sun, Christos Sakaridis, Jingyun Liang, Qi Jiang, Kailun Yang, Peng Sun, Yaozu Ye, Kaiwei Wang, Luc Van Gool
<span title="2022-04-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also introduce a novel symmetric cumulative event representation specifically for image deblurring as well as an event mask gated connection between the two stages of our network which helps avoid information  ...  In this paper, we rethink the eventbased image deblurring problem and unfold it into an end-to-end two-stage image restoration network.  ...  Motivated by the physical model of event-based image deblurring [27] , we design a symmetric cumulative event representation (SCER) specifically for deblurring and formulate a two-stage image restoration  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.00167v2">arXiv:2112.00167v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4nci4hufl5gmzfpa7wzqei3bya">fatcat:4nci4hufl5gmzfpa7wzqei3bya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211203054344/https://arxiv.org/pdf/2112.00167v1.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/22/35/223531a58536dbc4bb5a3296170fabf94247bc45.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.00167v2" 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>

Motion Blur Kernel Estimation via Deep Learning

Xiangyu Xu, Jinshan Pan, Yu-Jin Zhang, Ming-Hsuan Yang
<span title="">2018</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;
A straight-forward method to train the two-stage network is to use one channel for the third layer (i.e., c 3 = 1).  ...  To address these issues, we develop a CNN for the aforementioned two-stage process to restore sharp edges from blurred images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2753658">doi:10.1109/tip.2017.2753658</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28922121">pmid:28922121</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d3g2x2a6w5fzfiiyjs6dzjyzzy">fatcat:d3g2x2a6w5fzfiiyjs6dzjyzzy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180609234955/http://faculty.ucmerced.edu/mhyang/papers/tip18_deblur.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/07/2f/072fc7bb3155ab0a7af2d80006df801a27f127a3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2753658"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </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>
Image deblurring is a classic problem in low-level computer vision, which aims to recover a sharp image from a blurred input image.  ...  Recent advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed.  ...  For example, Schuler et al. [107] propose a two-stage cascaded network, see Figure 9 .  ... 
<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>

Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning [article]

Abdullah Abuolaim, Mahmoud Afifi, Michael S. Brown
<span title="2022-02-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We are interested in the latter task of defocus deblurring. In particular, we propose a single-image deblurring network that incorporates the two sub-aperture views into a multi-task framework.  ...  Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network's ability to learn to deblur the image.  ...  Acknowledgments A big thanks to David Ampofo for his amazing photography skills in collecting the images for our new DLDP dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05251v2">arXiv:2108.05251v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ihgmg2ivlfhdrhroeg3q3yhdbi">fatcat:ihgmg2ivlfhdrhroeg3q3yhdbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220212085622/https://arxiv.org/pdf/2108.05251v2.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/9f/30/9f30745f54f91b3ecea4f70e13ef0765685e02e7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05251v2" 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>

A Motion Deblur Method based on Multi-scale High Frequency Residual Image Learning

Keng-Hao Liu, Chia-Hung Yeh, Juh-Wei Chung, Chuan-Yu Chang
<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;
Followed by this trend, we first propose a two-stage deblurring module to recover the blur images of dynamic scenes based on high frequency residual image learning.  ...  The second stage calculates the difference of input image and initially deblurred image, referred to as residual image, and adopt an encoder-decoder network to refine the residual image.  ...  CONCLUSION In this paper, a motion deblurring method based on high-frequency residual image learning is presented. We first propose a two-stage deblurring module.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2985220">doi:10.1109/access.2020.2985220</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qmon6jfaonemlnhpme64osxspi">fatcat:qmon6jfaonemlnhpme64osxspi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108125400/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09055201.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/b1/de/b1dea2fea47d0ec7da5a84853d97033d429affce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2985220"> <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>

Single Image Joint Motion Deblurring and Super-Resolution Using the Multi-Scale Channel Attention Modules

Misak T. Shoyan, National Polytechnic University of Armenia
<span title="2021-12-14">2021</span> <i title="National Academy of Sciences of the Republic of Armenia"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fcwoqwudxfbrlluz6kbfqgdhoi" style="color: black;">Mathematical Problems of Computer Science</a> </i> &nbsp;
This work proposes a fully convolutional neural network to reconstruct high-resolution sharp images from the given motion blurry low-resolution images.  ...  The deblurring subnetwork is based on multi-stage progressive architecture, while the super-resolution subnetwork is designed using the multi-scale channel attention modules.  ...  Since, in the proposed architecture, the third stage of the MPRNet does not produce a deblurred image, a convolutional layer is added to generate the 𝐿 ̂3 image for the training phase only.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51408/1963-0076">doi:10.51408/1963-0076</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ulnois4kvzggvclqywynfcfcfy">fatcat:ulnois4kvzggvclqywynfcfcfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220426110438/https://mpcs.sci.am/index.php/mpcs/article/download/699/542/1180" 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/bd/b8bd41319bf2b1858a097d7ec3f65a6228a7e6ee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51408/1963-0076"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

NTIRE 2020 Challenge on Image and Video Deblurring [article]

Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee
<span title="2020-05-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
On Track 2, the image deblurring methods are executed on a mobile platform to find the balance of the running speed and the restoration accuracy.  ...  Track 1 aims to develop single-image deblurring methods focusing on restoration quality.  ...  IPCV IITM team -Track 1 IPCV IITM team buids a two-stage network based on DMPHN [87] and [67] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.01244v2">arXiv:2005.01244v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aoy3tyxlybefrd7yd5ywvr6jh4">fatcat:aoy3tyxlybefrd7yd5ywvr6jh4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200529002740/https://arxiv.org/pdf/2005.01244v2.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/4a/64/4a64aa20039c7995eb6ff21ae51f92f9e0e2ffe8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.01244v2" 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>

Balancing Heterogeneous Image Quality for Improved Cross-Spectral Face Recognition

Zhicheng Cao, Xi Cen, Heng Zhao, Liaojun Pang
<span title="2021-03-26">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
Results show that, in all cases, our proposed approach for quality balancing yields improved recognition performance, which is especially effective when involving SWIR images at a longer standoff.  ...  Specifically, this is realized through cascaded face enhancement that combines an existing denoising algorithm (BM3D) with a new deep-learning-based deblurring model we propose (named SVDFace).  ...  Acknowledgments: Special thanks to the CCF-IFAA Research Fund for greatly supporting the writing of the paper. To learn more about IFAA: www.ifaa.org.cn/en. Accessed on 25 March 2021.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21072322">doi:10.3390/s21072322</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33810407">pmid:33810407</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ilnzjxsm2jb2tbce2tgdwubtke">fatcat:ilnzjxsm2jb2tbce2tgdwubtke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210408060824/https://res.mdpi.com/d_attachment/sensors/sensors-21-02322/article_deploy/sensors-21-02322.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/07/b5/07b5b4628ad4dcc513d56d70fe68eacc35eed5aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21072322"> <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>

Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding [article]

Wenjia Niu, Kaihao Zhang, Wenhan Luo, Yiran Zhong, Xin Yu, Hongdong Li
<span title="2021-05-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images.  ...  Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images.  ...  ACKNOWLEDGMENT This work is funded in part by the ARC Centre of Excellence for Robotics Vision (CE140100016), ARC-Discovery (DP 190102261) and ARC-LIEF (190100080) grants, as well as a research grant from  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.13077v1">arXiv:2105.13077v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2mcty2fcijhyleyk3oshstmp4m">fatcat:2mcty2fcijhyleyk3oshstmp4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211021184351/https://arxiv.org/pdf/2105.13077v2.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/75/65/756538ac32a4f0171748b0d08f7174a59d5d985e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.13077v1" 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>

Handling noise in image deblurring via joint learning [article]

Si Miao, Yongxin Zhu
<span title="2020-01-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Slight residual noise in the denoised images could cause significant artifacts in the deblurring stage.  ...  To tackle this problem, we propose a cascaded framework consisting of a denoiser subnetwork and a deblurring subnetwork. In contrast to previous methods, we train the two subnetworks jointly.  ...  The slight noise are propagated into the deblurring networks and jeopardize the deblurring stage ( Fig. 1(f) ).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.09730v1">arXiv:2001.09730v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/myzszl5szfgypogya6gh3s657i">fatcat:myzszl5szfgypogya6gh3s657i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321115431/https://arxiv.org/pdf/2001.09730v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.09730v1" 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>

Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency [article]

Dong Huo, Abbas Masoumzadeh, Yee-Hong Yang
<span title="2022-04-21">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Some methods directly output the latent sharp image in one stage, while others utilize a multi-stage strategy (\eg multi-scale, multi-patch, or multi-temporal) to gradually restore the sharp image.  ...  To improve the training, we also propose a reblurring network to map the deblurred output back to the blurred input, which constrains the solution space.  ...  proposed deblurring network is end-to-end and contains only a single stage, which is more efficient and has a lower computational cost compared with other multi-stage methods. • We propose a new end-to-end  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14336v2">arXiv:2106.14336v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/67okpikuzzfzxpu7nvgzu2gpvu">fatcat:67okpikuzzfzxpu7nvgzu2gpvu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220426133808/https://arxiv.org/pdf/2106.14336v2.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/7b/72/7b72f5ba4c3cc7d90747a4303aead304a9cb6430.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14336v2" 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 2,199 results