BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_156@linklings.com
SUMMARY:MyStyle: A Personalized Generative Prior
DESCRIPTION:Technical Papers\n\nMyStyle: A Personalized Generative Prior\n
 \nNitzan, Aberman, Liba, He, Yarom...\n\nWe introduce MyStyle, a personali
 zed deep generative prior trained with a few shots of an individual. MySty
 le allows to reconstruct, enhance and edit images of a specific person, su
 ch that the output is faithful to the person’s key facial characteristics.
  Given a small reference set of portrait images of a person (∼ 100), we tu
 ne the weights of a pretrained StyleGAN face generator to form a local, lo
 w-dimensional, personalized manifold in the latent space.\nWe show that th
 is manifold constitutes a personalized region that spans latent codes asso
 ciated with diverse portrait images of the individual. Moreover, we demons
 trate that we obtain a personalized generative prior, and propose a unifie
 d approach to apply it to various ill-posed image enhancement problems, su
 ch as inpainting and super-resolution, as well as semantic editing. Using 
 the personalized generative prior we obtain outputs that exhibit high-fide
 lity to the input images and are also faithful to the key facial character
 istics of the individual in the reference set. We demonstrate our method w
 ith fair-use images of numerous widely recognizable individuals for whom w
 e have the prior knowledge for a qualitative evaluation\nof the expected o
 utcome. We evaluate our approach against few-shots baselines and show that
  our personalized prior, quantitatively and qualitatively, outperforms sta
 te-of-the-art alternatives.\n\nRegistration Category: FULL ACCESS, EXPERIE
 NCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n
 \nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_156&sess=sess15
 3
END:VEVENT
END:VCALENDAR