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:20230103T035312Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T140000
DTEND;TZID=Asia/Seoul:20221209T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess178_papers_454@linklings.com
SUMMARY:IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aw
 are Portrait Synthesis
DESCRIPTION:Technical Communications, Technical Papers\n\nIDE-3D: Interact
 ive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis\n
 \nSun, Wang, Shi, Wang, Liu...\n\nExisting 3D-aware facial generation meth
 ods face a dilemma in quality versus editability: they either generate edi
 table results in low resolution, or high quality ones with no editing flex
 ibility. In this work, we propose a new approach that brings the best of b
 oth worlds together. Our system consists of three major components: (1) a 
 3D-semantics-aware generative model that produces view-consistent, disenta
 ngled face images and semantic masks; (2) a hybrid GAN inversion approach 
 that initialize the latent codes from the semantic and texture encoder, an
 d further optimized them for faithful reconstruction; and (3) a canonical 
 editor that enables efficient manipulation of semantic masks in canonical 
 view and produces high quality editing results. Our approach is competent 
 for many applications, e.g. free-view face drawing, editing and style cont
 rol. Both quantitative and qualitative results show that our method reache
 s the state-of-the-art in terms of photorealism, faithfulness and efficien
 cy.\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: E
 NGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_454&sess=sess17
 8
END:VEVENT
END:VCALENDAR