BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Brisbane
X-LIC-LOCATION:Australia/Brisbane
BEGIN:STANDARD
DTSTART:19920301T030000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191203T080506Z
LOCATION:Plaza Meeting Room P2
DTSTART;TZID=Australia/Brisbane:20191119T165700
DTEND;TZID=Australia/Brisbane:20191119T171800
UID:siggraphasia_SIGGRAPH Asia 2019_sess115_papers_388@linklings.com
SUMMARY:The Relightables: Volumetric Performance Capture of Humans with Re
 alistic Relighting
DESCRIPTION:Technical Papers\n\nThe Relightables: Volumetric Performance C
 apture of Humans with Realistic Relighting\n\nGuo, Lincoln, Davidson, Busc
 h, Yu...\n\nWe present "The Relightables", a volumetric capture system for
  photorealistic and high quality relightable full-body performance capture
 . While significant progress has been made on volumetric capture systems, 
 focusing on 3D geometric reconstruction with high resolution textures, muc
 h less work has been done to recover photometric properties needed for rel
 ighting. Results from such systems lack high-frequency detail and the subj
 ect's shading is prebaked into the texture. In contrast, a large body of w
 ork has addressed relightable acquisition for image-based approaches, whic
 h photograph the subject under a set of basis lighting conditions and reco
 mbine the images to show the subject as they would appear in a target ligh
 ting environment. However, to date, these approaches have not been adapted
  for use in the context of a high-resolution volumetric capture system. Ou
 r method combines this ability to realistically relight humans for arbitra
 ry environments, with the benefits of free-viewpoint volumetric capture an
 d new levels of geometric accuracy for dynamic performances. Our subjects 
 are recorded inside a custom geodesic sphere outfitted with 331 custom col
 or LED lights, an array of high-resolution cameras, and a set of custom hi
 gh-resolution depth sensors. Our system innovates in multiple areas: First
 , we designed a novel active depth sensor to capture 12.4 MP depth maps, w
 hich we describe in detail. Second, we show how to design a hybrid geometr
 ic and machine learning reconstruction pipeline to process the high resolu
 tion input and output a volumetric video. Third, we generate temporally co
 nsistent reflectance maps for dynamic performers by leveraging the informa
 tion contained in two alternating color gradient illumination images acqui
 red at 60Hz. Multiple experiments, comparisons, and applications show that
  The Relightables significantly improves upon the level of realism in plac
 ing volumetrically captured human performances into arbitrary CG scenes.\n
 \nRegistration Category: Platinum Pass, Full Conference Pass, Full Confere
 nce One-Day Pass
URL:https://sa2019.conference-program.com/presentation?id=papers_388&sess=
 sess115
END:VEVENT
END:VCALENDAR