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:20260114T163645Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T143500
DTEND;TZID=Australia/Melbourne:20231214T144500
UID:siggraphasia_SIGGRAPH Asia 2023_sess130_papers_850@linklings.com
SUMMARY:360° Reconstruction From a Single Image Using Space Carved Outpain
 ting
DESCRIPTION:Nuri Ryu, Minsu Gong, and Geonung Kim (POSTECH); Joo-Haeng Lee
  (Pebblous Inc.); and Sunghyun Cho (POSTECH, Pebblous Inc.)\n\nWe introduc
 e POP3D, a novel framework that creates a full $360^\circ$-view 3D model f
 rom a single image. POP3D resolves two prominent issues that limit the sin
 gle-view reconstruction. Firstly, POP3D offers substantial generalizabilit
 y to arbitrary categories, a trait that previous methods struggle to achie
 ve. Secondly, POP3D further improves reconstruction fidelity and naturalne
 ss, a crucial aspect that concurrent works fall short of. POP3D marries th
 e strengths of four primary components: (1) a monocular depth and normal p
 redictor that serves to predict crucial geometric cues, (2) a space carvin
 g method capable of demarcating the potentially unseen portions of the tar
 get object, (3) a generative model pre-trained on a large-scale image data
 set that can complete unseen regions of the target, and (4) a neural impli
 cit surface reconstruction method tailored in reconstructing objects using
  RGB images along with monocular geometric cues. The combination of these 
 components enables POP3D to readily generalize across various in-the-wild 
 images and generate state-of-the-art reconstructions, outperforming simila
 r works by a significant margin.\n\nRegistration Category: Full Access\n\n
 Session Chair: Baoquan Chen (Peking University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_850&sess=sess130
END:VEVENT
END:VCALENDAR