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:20240214T070248Z
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:Technical Papers\n\nNuri Ryu, Minsu Gong, and Geonung Kim (POS
 TECH); Joo-Haeng Lee (Pebblous Inc.); and Sunghyun Cho (POSTECH, Pebblous 
 Inc.)\n\nWe introduce POP3D, a novel framework that creates a full $360^\c
 irc$-view 3D model from a single image. POP3D resolves two prominent issue
 s that limit the single-view reconstruction. Firstly, POP3D offers substan
 tial generalizability to arbitrary categories, a trait that previous metho
 ds struggle to achieve. Secondly, POP3D further improves reconstruction fi
 delity and naturalness, a crucial aspect that concurrent works fall short 
 of. POP3D marries the strengths of four primary components: (1) a monocula
 r depth and normal predictor that serves to predict crucial geometric cues
 , (2) a space carving method capable of demarcating the potentially unseen
  portions of the target object, (3) a generative model pre-trained on a la
 rge-scale image dataset that can complete unseen regions of the target, an
 d (4) a neural implicit surface reconstruction method tailored in reconstr
 ucting objects using RGB images along with monocular geometric cues. The c
 ombination of these components enables POP3D to readily generalize across 
 various in-the-wild images and generate state-of-the-art reconstructions, 
 outperforming similar works by a significant margin.\n\nRegistration Categ
 ory: Full Access\n\nSession Chair: Baoquan Chen (Peking University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_850&sess=sess130
END:VEVENT
END:VCALENDAR