BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171531Z
LOCATION:G610\, G Block\, Level 6
DTSTART;TZID=Asia/Tokyo:20241204T140000
DTEND;TZID=Asia/Tokyo:20241204T174500
UID:siggraphasia_SIGGRAPH Asia 2024_sess216_crs_103@linklings.com
SUMMARY:Automatic 3D modeling and exploration of indoor structures from pa
 noramic imagery
DESCRIPTION:Enrico Gobbetti (Center for Advanced Studies, Research and Dev
 elopment in Sardinia; Data and Quantum Computing); Enrico Gobbetti and Gio
 vanni Pintore (Center for Advanced Studies, Research and Development in Sa
 rdinia; National Research Center in High-Performance Computing, Big Data a
 nd Quantum Computing); and Marco Agus (Hamad Bin Khalifa University)\n\nSu
 rround-view panoramic imaging delivers extensive spatial coverage and is w
 idely supported by professional and commodity capture devices. Research on
  inferring and exploring 3D indoor models from 360-degree images has recen
 tly flourished, resulting in highly effective solutions. Nevertheless, cha
 llenges persist due to the complexity and variability of indoor environmen
 ts and issues with noisy and incomplete data. This course provides an up-t
 o-date integrative view of the field. After introducing a characterization
  of input sources, we define the structure of output models, the priors ex
 ploited to bridge the gap between imperfect input and desired output, and 
 the main characteristics of geometry reasoning and data-driven approaches.
  We then identify and discuss the main sub-problems in indoor reconstructi
 on from panoramas and review and analyze state-of-the-art solutions for in
 door capture, room modeling, integrated model computation, visual represen
 tation generation, and immersive exploration. Relevant examples of impleme
 nted pipelines are described, focusing on deep-learning solutions. We fina
 lly point out relevant research issues and analyze research trends.\n\nReg
 istration Category: Full Access, Full Access Supporter\n\nLanguage Format:
  English Language\n\n
URL:https://asia.siggraph.org/2024/program/?id=crs_103&sess=sess216
END:VEVENT
END:VCALENDAR