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_454@linklings.com
SUMMARY:IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aw
 are Portrait Synthesis
DESCRIPTION:Technical Papers\n\nIDE-3D: Interactive Disentangled Editing f
 or High-Resolution 3D-aware Portrait Synthesis\n\nSun, Wang, Shi, Wang, Li
 u...\n\nExisting 3D-aware facial generation methods face a dilemma in qual
 ity versus editability: they either generate editable results in low resol
 ution, or high quality ones with no editing flexibility. In this work, we 
 propose a new approach that brings the best of both worlds together. Our s
 ystem consists of three major components: (1) a 3D-semantics-aware generat
 ive model that produces view-consistent, disentangled face images and sema
 ntic masks; (2) a hybrid GAN inversion approach that initialize the latent
  codes from the semantic and texture encoder, and further optimized them f
 or faithful reconstruction; and (3) a canonical editor that enables effici
 ent manipulation of semantic masks in canonical view and produces high qua
 lity editing results. Our approach is competent for many applications, e.g
 . free-view face drawing, editing and style control. Both quantitative and
  qualitative results show that our method reaches the state-of-the-art in 
 terms of photorealism, faithfulness and efficiency.\n\nRegistration Catego
 ry: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITO
 R\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_454&sess=sess15
 3
END:VEVENT
END:VCALENDAR