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:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_317@linklings.com
SUMMARY:Online Scene CAD Recomposition via Autonomous Scanning
DESCRIPTION:Technical Papers\n\nChanghao Li and Junfu Guo (University of S
 cience and Technology of China), Ruizhen Hu (Shenzhen University), and Lig
 ang Liu (University of Science and Technology of China)\n\nAutonomous surf
 ace reconstruction of 3D scenes has been intensely studied in recent years
 , however, it is still difficult to accurately reconstruct all the surface
  details of complex scenes with complicated object relations and severe oc
 clusions, which makes the reconstruction results not suitable for direct u
 se in applications such as gaming and virtual reality. Therefore, instead 
 of reconstructing the detailed surfaces, we aim to recompose the scene wit
 h CAD models retrieved from a given dataset to faithfully reflect the obje
 ct geometry and arrangement in the given scene. Moreover, unlike most of t
 he previous works on scene CAD recomposition requiring an offline reconstr
 ucted scene or capture video as input, which leads to significant data red
 undancy, we proposed a novel online scene CAD recomposition method with au
 tonomous scanning, which efficiently recomposes the scene with the guidanc
 e of automatically optimized Next-Best-View (NBV) in a single online scann
 ing pass. Based on the key observation that spatial relation in the scene 
 can not only constrain the object pose and layout optimization but also gu
 ide the NBV generation, our system consists of two key modules: relation-g
 uided CAD recomposition module that uses relation-constrained global optim
 ization to get accurate object pose and layout estimation, and relation-aw
 are NBV generation module that makes the exploration during the autonomous
  scanning tailored for our composition task. Extensive experiments have be
 en conducted to show the superiority of our method over previous methods i
 n scanning efficiency and retrieval accuracy as well as the importance of 
 each key component of our method.\n\nRegistration Category: Full Access, E
 nhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_317&sess=sess209
END:VEVENT
END:VCALENDAR