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:20250110T023302Z
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:Courses\n\nEnrico Gobbetti (Center for Advanced Studies, Resea
 rch and Development in Sardinia; Data and Quantum Computing); Enrico Gobbe
 tti and Giovanni Pintore (Center for Advanced Studies, Research and Develo
 pment in Sardinia; National Research Center in High-Performance Computing,
  Big Data and Quantum Computing); and Marco Agus (Hamad Bin Khalifa Univer
 sity)\n\nSurround-view panoramic imaging delivers extensive spatial covera
 ge and is widely supported by professional and commodity capture devices. 
 Research on inferring and exploring 3D indoor models from 360-degree image
 s has recently flourished, resulting in highly effective solutions. Nevert
 heless, challenges persist due to the complexity and variability of indoor
  environments and issues with noisy and incomplete data. This course provi
 des an up-to-date integrative view of the field. After introducing a chara
 cterization of input sources, we define the structure of output models, th
 e priors exploited to bridge the gap between imperfect input and desired o
 utput, and the main characteristics of geometry reasoning and data-driven 
 approaches. We then identify and discuss the main sub-problems in indoor r
 econstruction from panoramas and review and analyze state-of-the-art solut
 ions for indoor capture, room modeling, integrated model computation, visu
 al representation generation, and immersive exploration. Relevant examples
  of implemented pipelines are described, focusing on deep-learning solutio
 ns. We finally point out relevant research issues and analyze research tre
 nds.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLangu
 age Format: English Language
URL:https://asia.siggraph.org/2024/program/?id=crs_103&sess=sess216
END:VEVENT
END:VCALENDAR