BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_471@linklings.com
SUMMARY:Differentiable Point-Based Radiance Fields for Efficient View Synt
 hesis
DESCRIPTION:Technical Papers\n\nDifferentiable Point-Based Radiance Fields
  for Efficient View Synthesis\n\nZhang, Baek, Rusinkiewicz, Heide\n\nWe pr
 opose a differentiable rendering algorithm for efficient novel view synthe
 sis. By departing from volume-based representations in favor of a learned 
 point representation, we improve on existing methods more than an order of
  magnitude in memory and runtime, both in training and inference. The meth
 od begins with a uniformly-sampled random point cloud and learns per-point
  position and view-dependent appearance, using a differentiable splat-base
 d renderer to evolve the model to match a set of input images. Our method 
 is up to 300x faster than NeRF in both training and inference, with only a
  marginal sacrifice in quality, while using less than 10~MB of memory for 
 a static scene. For dynamic scenes, our method trains two orders of magnit
 ude faster than STNeRF and renders at near interactive rate, while maintai
 ning high image quality and temporal coherence even without imposing any t
 emporal-coherency regularizers.\n\nRegistration Category: FULL ACCESS, EXP
 ERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLI
 SH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_471&sess=sess15
 3
END:VEVENT
END:VCALENDAR