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:20260114T163633Z
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_313@linklings.com
SUMMARY:Reconstructing Close Human Interaction from Multiple Views
DESCRIPTION:Qing Shuai (Zhejiang University); Zhiyuan Yu (Department of Ma
 thematics, Hong Kong University of Science and Technology); Zhize Zhou (Ca
 pital University of Physical Education and Sports); Lixin Fan and Haijun Y
 ang (WeBank); Can Yang (Department of Mathematics, Hong Kong University of
  Science and Technology); and Xiaowei Zhou (State Key Laboratory of CAD&CG
 , Zhejiang Univerisity)\n\nThis paper addresses the challenging task of re
 constructing the poses of multiple individuals engaged in close interactio
 ns, captured by multiple calibrated cameras. The difficulty arises from th
 e noisy or false 2D keypoint detection due to inter-person occlusion, the 
 heavy ambiguity to associate keypoints to individuals due to the close int
 eractions, and the scarcity of training data, as collecting and annotating
  extensive data in crowd scenes is resource-intensive. \n\nWe introduce a 
 novel learning-based system to address these challenges. Our approach cons
 tructs a 3D volume from multi-view 2D keypoint heatmaps, which is then fed
  into a conditional volumetric network to estimate the 3D pose for each in
 dividual.\n\nAs the network doesn't need images as input, we can leverage 
 known camera parameters from test scenes and a large quantity of existing 
 motion capture data to synthesize massive training data that mimics the di
 stribution of the real data in the test scenes.\n\nExtensive experiments a
 cross various camera setups and population sizes demonstrate that our appr
 oach significantly surpasses previous approaches in terms of both pose acc
 uracy and generalizability. The code will be made publicly available upon 
 acceptance of the paper.\n\nRegistration Category: Full Access, Enhanced A
 ccess, Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_313&sess=sess209
END:VEVENT
END:VCALENDAR