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_papers_662@linklings.com
SUMMARY:LiveNVS: Neural View Synthesis on Live RGB-D Streams
DESCRIPTION:Technical Papers\n\nLaura Fink (Friedrich-Alexander-Universitä
 t Erlangen-Nürnberg, Fraunhofer IIS); Darius Rückert and Linus Franke (Fri
 edrich-Alexander-Universität Erlangen-Nürnberg); Joachim Keinert (Fraunhof
 er IIS); and Marc Stamminger (Friedrich-Alexander-Universität Erlangen-Nür
 nberg)\n\nExisting real-time RGB-D reconstruction approaches, like Kinect 
 Fusion, lack real-time photo-realistic visualization. This is due to noisy
 , oversmoothed or incomplete geometry and blurry textures which are fused 
 from imperfect depth maps and camera poses. Recent neural rendering method
 s can overcome many of such artifacts but are mostly optimized for offline
  usage, hindering the integration into a live reconstruction pipeline.\n\n
 In this paper, we present LiveNVS, a system that allows for neural novel v
 iew synthesis on a live RGB-D input stream with very low latency and real-
 time rendering. Based on the RGB-D input stream, novel views are rendered 
 by projecting neural features into the target view via a densely fused dep
 th map and aggregating the features in image-space to a target feature map
 . A generalizable neural network then translates the target feature map in
 to a high-quality RGB image. LiveNVS achieves state-of-the-art neural rend
 ering quality of unknown scenes during capturing, allowing users to virtua
 lly explore the scene and assess reconstruction quality in real-time.\n\nR
 egistration Category: Full Access, Enhanced Access, Trade Exhibitor, Exper
 ience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_662&sess=sess209
END:VEVENT
END:VCALENDAR