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:20230103T035309Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T153000
DTEND;TZID=Asia/Seoul:20221207T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess163_papers_384@linklings.com
SUMMARY:AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridg
 ing
DESCRIPTION:Technical Communications, Technical Papers\n\nAgileAvatar: Sty
 lized 3D Avatar Creation via Cascaded Domain Bridging\n\nSang, Zhi, Song, 
 Liu, Lai...\n\nStylized 3D avatars have become increasingly prominent in o
 ur modern life. Creating these avatars manually usually involves laborious
  selection and adjustment of continuous and discrete parameters and is tim
 e-consuming for average users. Self-supervised approaches to automatically
  create 3D avatars from user selfies promise high quality with little anno
 tation cost but fall short in application to stylized avatars due to a lar
 ge style domain gap. We propose a novel self-supervised learning framework
  to create high-quality stylized 3D avatars with a mix of continuous and d
 iscrete parameters. Our cascaded domain bridging framework first leverages
  a modified portrait stylization approach to translate input selfies into 
 stylized avatar renderings as the targets for desired 3D avatars. Next, we
  find the best parameters of the avatars to match the stylized avatar rend
 erings through a differentiable imitator we train to mimic the avatar grap
 hics engine. To ensure we can effectively optimize the discrete parameters
 , we adopt a cascaded relaxation-and-search pipeline. We use a human prefe
 rence study to evaluate how well our method preserves user identity compar
 ed to previous work as well as manual creation. Our results achieve much h
 igher preference scores than previous work and close to those of manual cr
 eation. We also provide an ablation study to justify the design choices in
  our pipeline.\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\n
 Language: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_384&sess=sess16
 3
END:VEVENT
END:VCALENDAR