GAN-D: Generative Adversarial Networks for Image Deconvolution

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 347
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLee, Hayeonko
dc.contributor.authorKwak, Jin-Myungko
dc.contributor.authorBan, Byunghyunko
dc.contributor.authorNa, Seon-Jinko
dc.contributor.authorLee, Se Rako
dc.contributor.authorLee, Heung-Kyuko
dc.date.accessioned2017-11-20T08:20:23Z-
dc.date.available2017-11-20T08:20:23Z-
dc.date.created2017-11-13-
dc.date.created2017-11-13-
dc.date.created2017-11-13-
dc.date.issued2017-10-18-
dc.identifier.citationInternational Conference on Information and Communication Technology Convergence (ICTC), pp.132 - 137-
dc.identifier.issn2162-1233-
dc.identifier.urihttp://hdl.handle.net/10203/227008-
dc.description.abstractWe 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.languageEnglish-
dc.publisherIEEE Computer Society-
dc.titleGAN-D: Generative Adversarial Networks for Image Deconvolution-
dc.typeConference-
dc.identifier.wosid000426978700030-
dc.identifier.scopusid2-s2.0-85046893385-
dc.type.rimsCONF-
dc.citation.beginningpage132-
dc.citation.endingpage137-
dc.citation.publicationnameInternational Conference on Information and Communication Technology Convergence (ICTC)-
dc.identifier.conferencecountryKO-
dc.identifier.conferencelocationLotte City Hotel Jeju, Jeju Island-
dc.identifier.doi10.1109/ICTC.2017.8190958-
dc.contributor.localauthorLee, Heung-Kyu-
dc.contributor.nonIdAuthorBan, Byunghyun-
dc.contributor.nonIdAuthorLee, Se Ra-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0