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:20250110T023312Z
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:Technical Papers\n\nJianchun Chen and Jian Wang (Max Planck In
 stitute for Informatics; Saarbrücken Research Center for Visual Computing,
  Interaction and AI); Yinda Zhang, Rohit Pandey, and Thabo Beeler (Google 
 Inc.); and Marc Habermann and Christian Theobalt (Max Planck Institute for
  Informatics; Saarbrücken Research Center for Visual Computing, Interactio
 n and AI)\n\nImmersive VR telepresence ideally means being able to interac
 t and communicate with digital avatars that are indistinguishable from and
  precisely reflect the behaviour of their real counterparts. The core tech
 nical challenge is two fold: Creating a digital double that faithfully ref
 lects the real human and tracking the real human solely from egocentric se
 nsing devices that are lightweight and have a low energy consumption, e.g.
  a single RGB camera. Up to date, no unified solution to this problem exis
 ts as recent works solely focus on egocentric motion capture, only model t
 he head, or build avatars from multi-view captures. In this work, we, for 
 the first time in literature, propose a person-specific egocentric telepre
 sence approach, which jointly models the photoreal digital avatar while al
 so driving it from a single egocentric video. We first present a character
  model that is animatible, i.e. can be solely driven by skeletal motion, w
 hile being capable of modeling geometry and appearance. Then, we introduce
  a personalized egocentric motion capture component, which recovers full-b
 ody motion from an egocentric video. Finally, we apply the recovered pose 
 to our character model and perform a test-time mesh refinement such that t
 he geometry faithfully projects onto the egocentric view. To validate our 
 design choices, we propose a new and challenging benchmark, which provides
  paired egocentric and dense multi-view videos of real humans performing v
 arious motions. Our experiments demonstrate a clear step towards egocentri
 c and photoreal telepresence as our method outperforms baselines as well a
 s competing methods. For more details, code, and data, we refer to our pro
 ject page.\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nLanguage Format: English Language\n\nSession Chair: Manolis Savva (Simon 
 Fraser University)
URL:https://asia.siggraph.org/2024/program/?id=papers_626&sess=sess136
END:VEVENT
END:VCALENDAR