BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163652Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T095000
DTEND;TZID=Australia/Melbourne:20231214T100500
UID:siggraphasia_SIGGRAPH Asia 2023_sess124_tog_107@linklings.com
SUMMARY:NeRFFaceLighting: Implicit and Disentangled Face Lighting Represen
 tation Leveraging Generative Prior in Neural Radiance Fields
DESCRIPTION:Kaiwen Jiang (Institute of Computing Technology, Chinese Acade
 my of Sciences; Beijing Jiaotong University); Shu-Yu Chen (Institute of Co
 mputing Technology, Chinese Academy of Sciences); Hongbo Fu (School of Cre
 ative Media, City University of Hong Kong); and Lin Gao (Institute of Comp
 uting Technology, Chinese Academy of Sciences; University of Chinese Acade
 my of Sciences)\n\n3D-aware portrait lighting control is an emerging and p
 romising domain, thanks to the recent advance of generative adversarial ne
 tworks and neural radiance fields. Existing solutions typically try to dec
 ouple the lighting from the geometry and appearance for disentangled contr
 ol with an explicit lighting representation (e.g., Lambertian or Phong). H
 owever, they either are limited to a constrained lighting condition (e.g.,
  directional light) or demand a tricky-to-fetch dataset as supervision for
  the intrinsic compositions (e.g., the albedo). We propose NeRFFaceLightin
 g to explore an implicit representation for portrait lighting based on the
  pretrained tri-plane representation to address the above limitations. We 
 approach this disentangled lighting-control problem by distilling the shad
 ing from the original fused representation of both appearance and lighting
  (i.e., one tri-plane) to their disentangled representations (i.e., two tr
 i-planes) with the conditional discriminator to supervise the lighting eff
 ects. We further carefully design the regularization to reduce the ambigui
 ty of such decomposition and enhance the ability of generalization to unse
 en lighting conditions. Moreover, our method can be extended to enable 3D-
 aware real portrait relighting. Through extensive quantitative and qualita
 tive evaluations, we demonstrate the superior 3D-aware lighting control ab
 ility of our model compared to alternative and existing solutions.\n\nRegi
 stration Category: Full Access\n\nSession Chair: Lin Gao (University of Ch
 inese Academy of Sciences)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=tog_107&sess=sess124
END:VEVENT
END:VCALENDAR