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:20260114T163702Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T162500
DTEND;TZID=Australia/Melbourne:20231212T164000
UID:siggraphasia_SIGGRAPH Asia 2023_sess160_tog_103@linklings.com
SUMMARY:SparsePoser: Real-time Full-body Motion Reconstruction from Sparse
  Data
DESCRIPTION:Jose Luis Ponton and Haoran Yun (Universitat Politècnica de Ca
 talunya (UPC)); Andreas Aristidou (University of Cyprus, CYENS Centre of E
 xcellence); and Carlos Andujar and Nuria Pelechano (Universitat Politècnic
 a de Catalunya (UPC))\n\nAccurate and reliable human motion reconstruction
  is crucial for creating natural interactions of full-body avatars in Virt
 ual Reality (VR) and entertainment applications. As the Metaverse and soci
 al applications gain popularity, users are seeking cost-effective solution
 s to create full-body animations that are comparable in quality to those p
 roduced by commercial motion capture systems. In order to provide affordab
 le solutions though, it is important to minimize the number of sensors att
 ached to the subject's body. Unfortunately, reconstructing the full-body p
 ose from sparse data is a heavily under-determined problem. Some studies t
 hat use IMU sensors face challenges in reconstructing the pose due to posi
 tional drift and ambiguity of the poses. In recent years, some mainstream 
 VR systems have released 6-degree-of-freedom (6-DoF) tracking devices prov
 iding positional and rotational information. Nevertheless, most solutions 
 for reconstructing full-body poses rely on traditional inverse kinematics 
 (IK) solutions, which often produce non-continuous and unnatural poses. In
  this paper, we introduce SparsePoser, a novel deep learning-based solutio
 n for reconstructing a full-body pose from a reduced set of six tracking d
 evices. Our system incorporates a convolutional-based autoencoder that syn
 thesizes high-quality continuous human poses by learning the human motion 
 manifold from motion capture data. Then, we employ a learned IK component,
  made of multiple lightweight feed-forward neural networks, to adjust the 
 hands and feet towards the corresponding trackers. We extensively evaluate
  our method on publicly available motion capture datasets and with real-ti
 me live demos. We show that our method outperforms state-of-the-art techni
 ques using IMU sensors or 6-DoF tracking devices, and can be used for user
 s with different body dimensions and proportions.\n\nRegistration Category
 : Full Access\n\nSession Chair: Ioannis Karamouzas (University of Californ
 ia Riverside)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=tog_103&sess=sess160
END:VEVENT
END:VCALENDAR