Neural Crossbreed: Neural Based Image Metamorphosis

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 153
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorPark, Sanghunko
dc.contributor.authorSeo, Kwanggyoonko
dc.contributor.authorNoh, Junyongko
dc.date.accessioned2021-01-04T08:10:33Z-
dc.date.available2021-01-04T08:10:33Z-
dc.date.created2020-11-19-
dc.date.created2020-11-19-
dc.date.created2020-11-19-
dc.date.issued2020-12-
dc.identifier.citationACM TRANSACTIONS ON GRAPHICS, v.39, no.6, pp.1 - 15-
dc.identifier.issn0730-0301-
dc.identifier.urihttp://hdl.handle.net/10203/279450-
dc.description.abstractWe propose Neural Crossbreed, a feed-forward neural network that can learn a semantic change of input images in a latent space to create the morphing effect. Because the network learns a semantic change, a sequence of meaningful intermediate images can be generated without requiring the user to specify explicit correspondences. In addition, the semantic change learning makes it possible to perform the morphing between the images that contain objects with significantly different poses or camera views. Furthermore, just as in conventional morphing techniques, our morphing network can handle shape and appearance transitions separately by disentangling the content and the style transfer for rich usability. We prepare a training dataset for morphing using a pre-trained BigGAN, which generates an intermediate image by interpolating two latent vectors at an intended morphing value. This is the first attempt to address image morphing using a pre-trained generative model in order to learn semantic transformation. The experiments show that Neural Crossbreed produces high quality morphed images, overcoming various limitations associated with conventional approaches. In addition, Neural Crossbreed can be further extended for diverse applications such as multi-image morphing, appearance transfer, and video frame interpolation.-
dc.languageEnglish-
dc.publisherASSOC COMPUTING MACHINERY-
dc.titleNeural Crossbreed: Neural Based Image Metamorphosis-
dc.typeArticle-
dc.identifier.wosid000595589100064-
dc.identifier.scopusid2-s2.0-85097354760-
dc.type.rimsART-
dc.citation.volume39-
dc.citation.issue6-
dc.citation.beginningpage1-
dc.citation.endingpage15-
dc.citation.publicationnameACM TRANSACTIONS ON GRAPHICS-
dc.identifier.doi10.1145/3414685.3417797-
dc.contributor.localauthorNoh, Junyong-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorImage morphing-
dc.subject.keywordAuthorneural network-
dc.subject.keywordAuthorcontent and style disentanglement-
Appears in Collection
GCT-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0