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:20260114T163633Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_431@linklings.com
SUMMARY:Diffusion Posterior Illumination for Ambiguity-aware Inverse Rende
 ring
DESCRIPTION:Linjie Lyu (Max-Planck-Institut für Informatik), Ayush Tewari 
 (MIT CSAIL), Marc Habermann (Max-Planck-Institut für Informatik), Shunsuke
  Saito and Michael Zollhöfer (Reality Labs Research), and Thomas Leimkühle
 r and Christian Theobalt (Max-Planck-Institut für Informatik)\n\nInverse r
 endering, the process of inferring scene properties from images, is a chal
 lenging inverse problem. The task is ill-posed, as many different scene co
 nfigurations can give rise to the same image. Most existing solutions inco
 rporate priors into the inverse-rendering pipeline to encourage plausible 
 solutions, but they do not consider the inherent ambiguities and the multi
 -modal distribution of possible decompositions. In this work, we propose a
  novel scheme that integrates a denoising diffusion probabilistic model pr
 e-trained on natural illumination maps into an optimization framework invo
 lving a differentiable path tracer. The proposed method allows sampling fr
 om combinations of illumination and spatially-varying surface materials th
 at are, both, natural and explain the image observations. We further condu
 ct an extensive comparative study of different priors on illumination used
  in previous work on inverse rendering. Our method excels in recovering ma
 terials and producing highly realistic and diverse environment map samples
  that faithfully explain the illumination of the input images.\n\nRegistra
 tion Category: Full Access, Enhanced Access, Trade Exhibitor, Experience H
 all Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_431&sess=sess209
END:VEVENT
END:VCALENDAR