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:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_tog_107@linklings.com
SUMMARY:NeRFFaceLighting: Implicit and Disentangled Face Lighting Represen
 tation Leveraging Generative Prior in Neural Radiance Fields
DESCRIPTION:Technical Papers\n\nKaiwen Jiang (Institute of Computing Techn
 ology, Chinese Academy of Sciences; Beijing Jiaotong University); Shu-Yu C
 hen (Institute of Computing Technology, Chinese Academy of Sciences); Hong
 bo Fu (School of Creative Media, City University of Hong Kong); and Lin Ga
 o (Institute of Computing Technology, Chinese Academy of Sciences; Univers
 ity of Chinese Academy of Sciences)\n\n3D-aware portrait lighting control 
 is an emerging and promising domain, thanks to the recent advance of gener
 ative adversarial networks and neural radiance fields. Existing solutions 
 typically try to decouple the lighting from the geometry and appearance fo
 r disentangled control with an explicit lighting representation (e.g., Lam
 bertian or Phong). However, they either are limited to a constrained light
 ing condition (e.g., directional light) or demand a tricky-to-fetch datase
 t as supervision for the intrinsic compositions (e.g., the albedo). We pro
 pose NeRFFaceLighting to explore an implicit representation for portrait l
 ighting based on the pretrained tri-plane representation to address the ab
 ove limitations. We approach this disentangled lighting-control problem by
  distilling the shading from the original fused representation of both app
 earance and lighting (i.e., one tri-plane) to their disentangled represent
 ations (i.e., two tri-planes) with the conditional discriminator to superv
 ise the lighting effects. We further carefully design the regularization t
 o reduce the ambiguity of such decomposition and enhance the ability of ge
 neralization to unseen lighting conditions. Moreover, our method can be ex
 tended to enable 3D-aware real portrait relighting. Through extensive quan
 titative and qualitative evaluations, we demonstrate the superior 3D-aware
  lighting control ability of our model compared to alternative and existin
 g solutions.\n\nRegistration Category: Full Access, Enhanced Access, Trade
  Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=tog_107&sess=sess209
END:VEVENT
END:VCALENDAR