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:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T170500
DTEND;TZID=Asia/Tokyo:20241205T171600
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_papers_626@linklings.com
SUMMARY:EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Ava
 tars
DESCRIPTION:Jianchun Chen and Jian Wang (Max Planck Institute for Informat
 ics; Saarbrücken Research Center for Visual Computing, Interaction and AI)
 ; Yinda Zhang, Rohit Pandey, and Thabo Beeler (Google Inc.); and Marc Habe
 rmann and Christian Theobalt (Max Planck Institute for Informatics; Saarbr
 ücken Research Center for Visual Computing, Interaction and AI)\n\nImmersi
 ve VR telepresence ideally means being able to interact and communicate wi
 th digital avatars that are indistinguishable from and precisely reflect t
 he behaviour of their real counterparts. The core technical challenge is t
 wo fold: Creating a digital double that faithfully reflects the real human
  and tracking the real human solely from egocentric sensing devices that a
 re lightweight and have a low energy consumption, e.g. a single RGB camera
 . Up to date, no unified solution to this problem exists as recent works s
 olely focus on egocentric motion capture, only model the head, or build av
 atars from multi-view captures. In this work, we, for the first time in li
 terature, propose a person-specific egocentric telepresence approach, whic
 h jointly models the photoreal digital avatar while also driving it from a
  single egocentric video. We first present a character model that is anima
 tible, i.e. can be solely driven by skeletal motion, while being capable o
 f modeling geometry and appearance. Then, we introduce a personalized egoc
 entric motion capture component, which recovers full-body motion from an e
 gocentric video. Finally, we apply the recovered pose to our character mod
 el and perform a test-time mesh refinement such that the geometry faithful
 ly projects onto the egocentric view. To validate our design choices, we p
 ropose a new and challenging benchmark, which provides paired egocentric a
 nd dense multi-view videos of real humans performing various motions. Our 
 experiments demonstrate a clear step towards egocentric and photoreal tele
 presence as our method outperforms baselines as well as competing methods.
  For more details, code, and data, we refer to our project page.\n\nRegist
 ration Category: Full Access, Full Access Supporter\n\nLanguage Format: En
 glish Language\n\nSession Chair: Manolis Savva (Simon Fraser University)\n
 \n
URL:https://asia.siggraph.org/2024/program/?id=papers_626&sess=sess136
END:VEVENT
END:VCALENDAR