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:20260114T163642Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T143500
DTEND;TZID=Australia/Melbourne:20231213T145000
UID:siggraphasia_SIGGRAPH Asia 2023_sess128_papers_914@linklings.com
SUMMARY:GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fiel
 ds
DESCRIPTION:Barbara Roessle and Norman Müller (Technical University of Mun
 ich); Lorenzo Porzi, Samuel Rota Bulò, and Peter Kontschieder (Meta Realit
 y Labs); and Matthias Niessner (Technical University of Munich)\n\nNeural 
 Radiance Fields (NeRF) have shown impressive novel view synthesis results;
  nonetheless, even thorough recordings yield imperfections in reconstructi
 ons, for instance due to poorly observed areas or minor lighting changes.\
 nOur goal is to mitigate these imperfections from various sources with a j
 oint solution: we take advantage of the ability of generative adversarial 
 networks (GANs) to produce realistic images and use them to enhance realis
 m in 3D scene reconstruction with NeRFs. \nTo this end, we learn the patch
  distribution of a scene using an adversarial discriminator, which provide
 s feedback to the radiance field reconstruction, thus improving realism in
  a 3D-consistent fashion. \nThereby, rendering artifacts are repaired dire
 ctly in the underlying 3D representation by imposing multi-view path rende
 ring constraints. \nIn addition, we condition a generator with multi-resol
 ution NeRF renderings which is adversarially trained to further improve re
 ndering quality. \nWe demonstrate that our approach significantly improves
  rendering quality, e.g., nearly halving LPIPS scores compared to Nerfacto
  while at the same time improving PSNR by 1.4dB on the advanced indoor sce
 nes of Tanks and Temples.\n\nRegistration Category: Full Access\n\nSession
  Chair: Jianfei Cai (Monash University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_914&sess=sess128
END:VEVENT
END:VCALENDAR