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_118@linklings.com
SUMMARY:NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fiel
 ds
DESCRIPTION:Technical Papers\n\nNeRFFaceEditing: Disentangled Face Editing
  in Neural Radiance Fields\n\nJiang, Chen, Liu, Fu, Gao\n\nRecent methods 
 for synthesizing 3D-aware face images have achieved rapid development than
 ks to neural radiance fields, allowing for high quality and fast inference
  speed. However, existing solutions for editing facial geometry and appear
 ance independently usually require retraining and are not optimized for th
 e recent work of generation, thus tending to lag behind the generation pro
 cess. To address these issues, we introduce NeRFFaceEditing, which enables
  editing and decoupling geometry and appearance in the pretrained tri-plan
 e-based neural radiance field while retaining its high quality and fast in
 ference speed. Our key idea for disentanglement is to use the statistics o
 f the tri-plane to represent the high-level appearance of its correspondin
 g facial volume. Moreover, we leverage a generated 3D-continuous semantic 
 mask as an intermediary for geometry editing. We devise a geometry decoder
  (whose output is unchanged when the appearance changes) and an appearance
  decoder. The geometry decoder aligns the original facial volume with the 
 semantic mask volume. We also enhance the disentanglement by explicitly re
 gularizing rendered images with the same appearance but different geometry
  to be similar in terms of color distribution for each facial component se
 parately. Our method allows users to edit via semantic masks with decouple
 d control of geometry and appearance. Both qualitative and quantitative ev
 aluations show the superior geometry and appearance control abilities of o
 ur method compared to existing and alternative solutions.\n\nRegistration 
 Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EX
 HIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_118&sess=sess15
 3
END:VEVENT
END:VCALENDAR