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:20240214T070242Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_tog_103@linklings.com
SUMMARY:SparsePoser: Real-time Full-body Motion Reconstruction from Sparse
  Data
DESCRIPTION:Technical Papers\n\nJose Luis Ponton and Haoran Yun (Universit
 at Politècnica de Catalunya (UPC)); Andreas Aristidou (University of Cypru
 s, CYENS Centre of Excellence); and Carlos Andujar and Nuria Pelechano (Un
 iversitat Politècnica de Catalunya (UPC))\n\nAccurate and reliable human m
 otion reconstruction is crucial for creating natural interactions of full-
 body avatars in Virtual Reality (VR) and entertainment applications. As th
 e Metaverse and social applications gain popularity, users are seeking cos
 t-effective solutions to create full-body animations that are comparable i
 n quality to those produced by commercial motion capture systems. In order
  to provide affordable solutions though, it is important to minimize the n
 umber of sensors attached to the subject's body. Unfortunately, reconstruc
 ting the full-body pose from sparse data is a heavily under-determined pro
 blem. Some studies that use IMU sensors face challenges in reconstructing 
 the pose due to positional drift and ambiguity of the poses. In recent yea
 rs, some mainstream VR systems have released 6-degree-of-freedom (6-DoF) t
 racking devices providing positional and rotational information. Neverthel
 ess, 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 le
 arning-based solution for reconstructing a full-body pose from a reduced s
 et of six tracking devices. Our system incorporates a convolutional-based 
 autoencoder that synthesizes high-quality continuous human poses by learni
 ng the human motion manifold from motion capture data. Then, we employ a l
 earned IK component, made of multiple lightweight feed-forward neural netw
 orks, to adjust the hands and feet towards the corresponding trackers. We 
 extensively evaluate our method on publicly available motion capture datas
 ets and with real-time live demos. We show that our method outperforms sta
 te-of-the-art techniques using IMU sensors or 6-DoF tracking devices, and 
 can be used for users with different body dimensions and proportions.\n\nR
 egistration Category: Full Access, Enhanced Access, Trade Exhibitor, Exper
 ience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=tog_103&sess=sess209
END:VEVENT
END:VCALENDAR