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:20260114T163654Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T105500
DTEND;TZID=Australia/Melbourne:20231215T110500
UID:siggraphasia_SIGGRAPH Asia 2023_sess154_papers_729@linklings.com
SUMMARY:MCNeRF: Monte Carlo Rendering and Denoising for Real-Time NeRFs
DESCRIPTION:Kunal Gupta (UC San Diego); Milos Hasan, Zexiang Xu, Fujun Lua
 n, Kalyan Sunkavalli, and Xin Sun (Adobe Inc.); Manmohan Chandraker (UC Sa
 n Diego); and Sai Bi (Adobe Inc.)\n\nThe volume rendering step used in Neu
 ral Radiance Fields (NeRFs) produces highly photorealistic results, but is
  inherently slow because it evaluates an MLP at a large number of sample p
 oints per ray. Previous work has addressed this by either proposing neural
  scene representations that are faster to evaluate or by pre-computing (an
 d approximating) scene properties to reduce render times. In this work, we
  propose \mcnerf, a \emph{general} Monte Carlo-based rendering algorithm t
 hat can speed up \emph{any} NeRF representation. We show that the NeRF vol
 ume rendering integral can be efficiently computed via Monte Carlo integra
 tion using an importance sampling scheme based on ray transmittance distri
 butions. This allows us to, at render time, vary the number of color sampl
 es evaluated per ray to trade-off visual quality (noise variance) against 
 performance. These noisy Monte Carlo estimates can be further denoised usi
 ng an inexpensive image-space denoiser trained per-scene. We demonstrate t
 hat \mcnerf can be used to speed up NeRF representations like TensoRF and 
 Instant-NGP by $7\times$ while closely matching their visual quality and w
 ithout making the scene approximations that real-time NeRF rendering metho
 ds usually make.\n\nRegistration Category: Full Access\n\nSession Chair: Y
 uchi Huo (Zhejiang University, Korea Advanced Institute of Science and Tec
 hnology)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_729&sess=sess154
END:VEVENT
END:VCALENDAR