Show simple item record

dc.contributor.authorLutz, Sebastian
dc.contributor.authorAmplianitis, Konstantinos
dc.contributor.authorSmolic, Aljosa
dc.date.accessioned2019-11-13T16:11:20Z
dc.date.available2019-11-13T16:11:20Z
dc.date.issued2018
dc.date.submitted2018en
dc.identifier.citationLutz, S., Aplianitis, K. & Smolic, A., AlphaGAN: Generative adversarial networks for natural image matting, 2018en
dc.identifier.otherY
dc.identifier.urihttp://hdl.handle.net/2262/90465
dc.descriptionPUBLISHEDen
dc.description.abstractWe present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial loss from the discriminator that is trained to classify wellcomposited images. Further, we improve existing encoder-decoder architectures to better deal with the spatial localization issues inherited in convolutional neural networks (CNN) by using dilated convolutions to capture global context information without downscaling feature maps and losing spatial information. We present state-of-the-art results on the alphamatting online benchmark for the gradient error and give comparable results in others. Our method is particularly well suited for fine structures like hair, which is of great importance in practical matting applications, e.g. in film/TV production.en
dc.language.isoenen
dc.rightsYen
dc.subjectConvolutional neural networksen
dc.subjectNatural image mattingen
dc.titleAlphaGAN: Generative adversarial networks for natural image mattingen
dc.typeConference Paperen
dc.contributor.sponsorScience Foundation Ireland (SFI)en
dc.type.supercollectionscholarly_publicationsen
dc.type.supercollectionrefereed_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/smolica
dc.identifier.rssinternalid199005
dc.rights.ecaccessrightsopenAccess
dc.contributor.sponsorGrantNumber15/RP/2776en
dc.subject.TCDThemeCreative Technologiesen
dc.subject.TCDTagMultimedia & Creativityen
dc.identifier.rssurihttps://v-sense.scss.tcd.ie/wp-content/uploads/2018/07/AlphaGAN_arxiv.pdf
dc.status.accessibleNen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record