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:20240214T070246Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T091500
DTEND;TZID=Australia/Melbourne:20231214T092500
UID:siggraphasia_SIGGRAPH Asia 2023_sess124_papers_612@linklings.com
SUMMARY:Neural Point-based Volumetric Avatar: Surface-guided Neural Points
  for Efficient and Photorealistic Volumetric Head Avatar
DESCRIPTION:Technical Papers, TOG\n\nCong Wang (Tsinghua University); Di K
 ang, Yan-Pei Cao, Linchao Bao, and Ying Shan (Tencent); and Song-Hai Zhang
  (Tsinghua University)\n\nRendering photo-realistic and vividly moving hum
 an heads is very important for pleasant and immersive experience in AR/VR 
 and video conferencing. However, existing methods usually struggle to mode
 l challenging facial regions (e.g., mouth interior, eyes, hair/beard), res
 ulting in unrealistic and blurry results. In this paper, we propose Neural
  Point-based Volumetric Avatar (NPVA), which discards predefined connectiv
 ity and hard correspondence imposed by mesh-based methods (i.e. neural poi
 nts) and adopts neural volume rendering. Specifically, the neural points a
 re constrained around the surface of the target expression via a high-reso
 lution UV displacement map, achieving increased modeling capacity and more
  accurate control. We propose three technical innovations to improve the r
 endering and training efficiency, including a patch-wise depth-guided (sha
 ding point) sampling strategy, a lightweight radiance decoding process, an
 d a Grid-Error-Patch (GEP) ray sampling strategy during training. By desig
 n, our NPVA can better handle topologically changing regions and thin stru
 ctures, and can be animated with accurate expression control.\n\nRegistrat
 ion Category: Full Access\n\nSession Chair: Lin Gao (University of Chinese
  Academy of Sciences)
URL:https://asia.siggraph.org/2023/full-program?id=papers_612&sess=sess124
END:VEVENT
END:VCALENDAR