DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hayeon | ko |
dc.contributor.author | Kwak, Jin-Myung | ko |
dc.contributor.author | Ban, Byunghyun | ko |
dc.contributor.author | Na, Seon-Jin | ko |
dc.contributor.author | Lee, Se Ra | ko |
dc.contributor.author | Lee, Heung-Kyu | ko |
dc.date.accessioned | 2017-11-20T08:20:23Z | - |
dc.date.available | 2017-11-20T08:20:23Z | - |
dc.date.created | 2017-11-13 | - |
dc.date.created | 2017-11-13 | - |
dc.date.created | 2017-11-13 | - |
dc.date.issued | 2017-10-18 | - |
dc.identifier.citation | International Conference on Information and Communication Technology Convergence (ICTC), pp.132 - 137 | - |
dc.identifier.issn | 2162-1233 | - |
dc.identifier.uri | http://hdl.handle.net/10203/227008 | - |
dc.description.abstract | We propose new generative adversarial networks for generalized image deconvolution, GAN-D. Most of the previous researches concentrate to specific sub-topic of image deconvolution or generative image deconvolution models with a strong assumption. However, our network restores visual data from distorted images applied multiple dominant degradation problems such as noise, blur, saturation, compression without any prior information. As a generator, we leverage convolutional neural networks based ODCNN [12] which perform generalized image deconvolution with a decent performance, and we use VGGNet [11] to distinguish true/fake of an input image as a discriminator. We devise the loss function of the generator of GAN-D which combines mean square error (MSE) of network output and ground-truth images to traditional adversarial loss of GAN. This loss function and the presence of discriminator reinforces the generator to produce more high-quality images than the original model structured with a single convolutional neural network. During experiments with four datasets, we find that our network has higher PSNR/SSIM values and qualitative results than ODCNN. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | GAN-D: Generative Adversarial Networks for Image Deconvolution | - |
dc.type | Conference | - |
dc.identifier.wosid | 000426978700030 | - |
dc.identifier.scopusid | 2-s2.0-85046893385 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 132 | - |
dc.citation.endingpage | 137 | - |
dc.citation.publicationname | International Conference on Information and Communication Technology Convergence (ICTC) | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Lotte City Hotel Jeju, Jeju Island | - |
dc.identifier.doi | 10.1109/ICTC.2017.8190958 | - |
dc.contributor.localauthor | Lee, Heung-Kyu | - |
dc.contributor.nonIdAuthor | Ban, Byunghyun | - |
dc.contributor.nonIdAuthor | Lee, Se Ra | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.