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:20260817T171533Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T094600
DTEND;TZID=Asia/Tokyo:20241206T095800
UID:siggraphasia_SIGGRAPH Asia 2024_sess139_papers_1121@linklings.com
SUMMARY:The Lips, the Teeth, the tip of the Tongue: LTT Tracking
DESCRIPTION:Feisal Rasras, Stanislav Pidhorskyi, and Tomas Simon (Reality 
 Labs Research); Hallison Paz (Instituto Nacional de Matemática Pura e Apli
 cada (IMPA)); and He Wen, Jason Saragih, and Javier Romero (Reality Labs R
 esearch)\n\nA mesh-based generative model of the inner-mouth system is pre
 sented, which includes teeth and gums for the upper and lower jaw, the ton
 gue, and their placement inside the human head. The model is capable of ca
 pturing person-specific detail, enabling the creation of highly accurate a
 vatars that exceed the quality of prior mesh-based representations. The me
 thod combines data from dental mouth scans and facial performances capture
 d in a multi-camera capture rig. The system employs a precise segmentation
  model that can differentiate complex tongue motion. A novel inverse-rende
 ring formulation is used in a staged modeling procedure, producing accurat
 e registration of tongue, teeth, and jaw as well as improved disentangleme
 nt of non-rigid face motion from rigid head motion. The system is demonstr
 ated on novel held-out subjects, where we demonstrate highly accurate reco
 nstructions that exceed prior mesh-based avatar representations.\n\nRegist
 ration Category: Full Access, Full Access Supporter\n\nLanguage Format: En
 glish Language\n\nSession Chair: Kui Wu (LIGHTSPEED)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_1121&sess=sess139
END:VEVENT
END:VCALENDAR