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:20240214T070245Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T154500
DTEND;TZID=Australia/Melbourne:20231213T160000
UID:siggraphasia_SIGGRAPH Asia 2023_sess125_tog_109@linklings.com
SUMMARY:Spatiotemporally Consistent HDR Indoor Lighting Estimation
DESCRIPTION:Technical Papers, TOG\n\nZhengqin Li (Meta, University of Cali
 fornia San Diego); Yu Li and Mikhail Okunev (Meta); Manmohan Chandraker (U
 niversity of California San Diego); and Zhao Dong (Meta)\n\nWe propose a p
 hysically-motivated deep learning framework to solve a general version of 
 the challenging indoor lighting estimation problem. Given a single LDR ima
 ge with a depth map, our method predicts spatially consistent lighting at 
 any given image position. Particularly, when the input is an LDR video seq
 uence, our framework not only progressively refines the lighting predictio
 n as it sees more regions, but also preserves temporal consistency by keep
 ing the refinement smooth. Our framework reconstructs a spherical Gaussian
  lighting volume (SGLV) through a tailored 3D encoder-decoder, which enabl
 es spatially consistent lighting prediction through volume ray\ntracing, a
  hybrid blending network for detailed environment maps, an innetwork Monte
 -Carlo rendering layer to enhance photorealism for virtual object insertio
 n, and recurrent neural networks (RNN) to achieve temporally consistent li
 ghting prediction with a video sequence as the input. For training, we sig
 nificantly enhance the OpenRooms public dataset of photorealistic syntheti
 c indoor scenes with around 360K HDR environment maps of much higher resol
 ution and 38K video sequences, rendered with GPU-based path tracing. Exper
 iments show that our framework achieves lighting prediction with higher qu
 ality compared to state-of-the-art single-image or video-based methods, le
 ading to photorealistic AR applications such as object insertion.\n\nRegis
 tration Category: Full Access\n\nSession Chair: Michael Gharbi (Adobe, MIT
 )
URL:https://asia.siggraph.org/2023/full-program?id=tog_109&sess=sess125
END:VEVENT
END:VCALENDAR