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:20230103T035311Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221208T153000
DTEND;TZID=Asia/Seoul:20221208T170000
UID:siggraphasia_SIGGRAPH Asia 2022_sess166_papers_558@linklings.com
SUMMARY:Production-Ready Face Re-Aging for Visual Effects
DESCRIPTION:Technical Communications, Technical Papers\n\nProduction-Ready
  Face Re-Aging for Visual Effects\n\nZoss, Chandran, Sifakis, Gross, Gotar
 do...\n\nPhotorealistic digital re-aging of faces in video is becoming inc
 reasingly common in entertainment and advertising.  But the predominant 2D
  painting workflow often requires frame-by-frame manual work that can take
  days to accomplish, even by skilled artists.  Although research on facial
  image re-aging has attempted to automate and solve this problem, current 
 techniques are of little practical use as they typically suffer from facia
 l identity loss, poor resolution, and unstable results across subsequent v
 ideo frames. In this paper, we present the first practical, fully-automati
 c and production-ready method for re-aging faces in video images.  Our fir
 st key insight is in addressing the problem of collecting longitudinal tra
 ining data for learning to re-age faces over extended periods of time, a t
 ask that is nearly impossible to accomplish for a large number of real peo
 ple. We show how such a longitudinal dataset can be constructed by leverag
 ing the current state-of-the-art in facial re-aging that, although failing
  on real images, do provide photoreal re-aging results on synthetic faces.
  Our second key insight is then to leverage such synthetic data and formul
 ate facial re-aging as a practical image-to-image translation task that ca
 n be performed by training a well-understood U-Net architecture, without t
 he need for more complex network designs. We demonstrate how the simple U-
 Net leads to surprisingly better results for re-aging real faces on video,
  with unprecedented temporal stability and preservation of facial identity
  across variable viewpoints and lighting conditions. Finally, our new face
  re-aging network (FRAN) incorporates simple and intuitive mechanisms that
  provides artists with localized control and creative freedom to direct an
 d fine-tune the re-aging effect, a feature that is largely important in re
 al production pipelines and often overlooked in related research work.\n\n
 Registration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\
 n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_558&sess=sess16
 6
END:VEVENT
END:VCALENDAR