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:20230103T035306Z LOCATION:Auditorium\, Level 5\, West Wing DTSTART;TZID=Asia/Seoul:20221206T100000 DTEND;TZID=Asia/Seoul:20221206T120000 UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_384@linklings.com SUMMARY:AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridg ing DESCRIPTION:Technical Papers\n\nAgileAvatar: Stylized 3D Avatar Creation v ia Cascaded Domain Bridging\n\nSang, Zhi, Song, Liu, Lai...\n\nStylized 3D avatars have become increasingly prominent in our modern life. Creating t hese avatars manually usually involves laborious selection and adjustment of continuous and discrete parameters and is time-consuming for average us ers. Self-supervised approaches to automatically create 3D avatars from us er selfies promise high quality with little annotation cost but fall short in application to stylized avatars due to a large style domain gap. We pr opose a novel self-supervised learning framework to create high-quality st ylized 3D avatars with a mix of continuous and discrete parameters. Our ca scaded domain bridging framework first leverages a modified portrait styli zation 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 renderings through a different iable imitator we train to mimic the avatar graphics engine. To ensure we can effectively optimize the discrete parameters, we adopt a cascaded rela xation-and-search pipeline. We use a human preference study to evaluate ho w well our method preserves user identity compared to previous work as wel l as manual creation. Our results achieve much higher preference scores th an previous work and close to those of manual creation. We also provide an ablation study to justify the design choices in our pipeline.\n\nRegistra tion Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRA DE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON URL:https://sa2022.siggraph.org/en/full-program/?id=papers_384&sess=sess15 3 END:VEVENT END:VCALENDAR