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 C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T145000
DTEND;TZID=Australia/Melbourne:20231213T150500
UID:siggraphasia_SIGGRAPH Asia 2023_sess164_tog_108@linklings.com
SUMMARY:High-Resolution Volumetric Reconstruction for Clothed Humans
DESCRIPTION:Technical Papers, TOG\n\nSicong Tang (Simon Fraser University)
 ; Guangyuan Wang, Qing Ran, Lingzhi Li, and Li Shen (Alibaba); and Ping Ta
 n (Simon Fraser University)\n\nWe present a novel method for reconstructin
 g clothed humans from a sparse set of, e.g., 1-6 RGB images. We revisit th
 e volumetric approach and demonstrate that better performance can be achie
 ved with proper system design. The volumetric representation offers signif
 icant advantages in leveraging 3D spatial context through 3D convolutions,
  and the notorious quantization error is largely negligible with a reasona
 bly large yet affordable volume resolution, e.g., 512. Extensive experimen
 tal results show that our method significantly reduces the mean point-to-s
 urface (P2S) precision of state-of-the-art methods by more than 50% to ach
 ieve approximately 2mm accuracy with a 512 volume resolution. Additionally
 , images rendered from our textured model achieve a higher peak signal-to-
 noise ratio (PSNR) compared to state-of-the-art methods.\n\nRegistration C
 ategory: Full Access\n\nSession Chair: Parag Chaudhuri (Indian Institute o
 f Technology Bombay)
URL:https://asia.siggraph.org/2023/full-program?id=tog_108&sess=sess164
END:VEVENT
END:VCALENDAR