StylePortraitVideo: Editing Portrait Videos with Expression Optimization

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 87
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorSeo, Kwanggunko
dc.contributor.authorNoh, Junyongko
dc.contributor.authorOh, Seoung Wugko
dc.contributor.authorLu, Jingwanko
dc.contributor.authorLee, Joon-Youngko
dc.contributor.authorKim, Seonghyeonko
dc.date.accessioned2022-12-07T08:01:26Z-
dc.date.available2022-12-07T08:01:26Z-
dc.date.created2022-12-01-
dc.date.created2022-12-01-
dc.date.created2022-12-01-
dc.date.issued2022-10-06-
dc.identifier.citationPacific Graphics 2022-
dc.identifier.urihttp://hdl.handle.net/10203/301929-
dc.description.abstractHigh-quality portrait image editing has been made easier by recent advances in GANs (e.g., StyleGAN) and GAN inversion methods that project images onto a pre-trained GAN’s latent space. However, extending the existing image editing methods, it is hard to edit videos to produce temporally coherent and natural-looking videos. We find challenges in reproducing diverse video frames and preserving the natural motion after editing. In this work, we propose solutions for these challenges. First, we propose a video adaptation method that enables the generator to reconstruct the original input identity, unusual poses, and expressions in the video. Second, we propose an expression dynamics optimization that tweaks the latent codes to maintain the meaningful motion in the original video. Based on these methods, we build a StyleGAN-based high-quality portrait video editing system that can edit videos in the wild in a temporally coherent way at up to 4K resolution.-
dc.languageEnglish-
dc.publisherAsiaGraphics Association.-
dc.titleStylePortraitVideo: Editing Portrait Videos with Expression Optimization-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationnamePacific Graphics 2022-
dc.identifier.conferencecountryJA-
dc.identifier.conferencelocationKyoto International Conference Center-
dc.contributor.localauthorNoh, Junyong-
dc.contributor.nonIdAuthorOh, Seoung Wug-
dc.contributor.nonIdAuthorLu, Jingwan-
dc.contributor.nonIdAuthorLee, Joon-Young-
Appears in Collection
GCT-Conference Papers(학술회의논문)
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