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:20240214T070247Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T115000
DTEND;TZID=Australia/Melbourne:20231214T120000
UID:siggraphasia_SIGGRAPH Asia 2023_sess170_papers_291@linklings.com
SUMMARY:Single-Image 3D Human Digitization with Shape-guided Diffusion
DESCRIPTION:Technical Papers\n\nBadour AlBahar (Kuwait University); Shunsu
 ke Saito, Hung-Yu Tseng, Changil Kim, and Johannes Kopf (Meta); and Jia-Bi
 n Huang (University of Maryland)\n\nWe present an approach to generate a 3
 60-degree view of a person with a consistent, high-resolution appearance f
 rom a single input image. NeRF and its variants typically require videos o
 r images from different viewpoints. Most existing approaches taking monocu
 lar input either rely on ground-truth 3D scans for supervision or lack 3D 
 consistency. While recent 3D generative models show promise of 3D consiste
 nt human digitization, these approaches do not generalize well to diverse 
 clothing appearances, and the results lack photorealism. Unlike existing w
 ork, we utilize high-capacity 2D diffusion models pretrained for general i
 mage synthesis tasks as an appearance prior of clothed humans. To achieve 
 better 3D consistency while retaining the input identity, we progressively
  synthesize multiple views of the human in the input image by inpainting m
 issing regions with shape-guided diffusion conditioned on silhouette and s
 urface normal. We then fuse these synthesized multi-view images via invers
 e rendering to obtain a fully textured high-resolution 3D mesh of the give
 n person. Experiments show that our approach outperforms prior methods and
  achieves photorealistic 360-degree synthesis of a wide range of clothed h
 umans with complex textures from a single image.\n\nRegistration Category:
  Full Access\n\nSession Chair: Xiangyu Xu (Xi'an Jiaotong University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_291&sess=sess170
END:VEVENT
END:VCALENDAR