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:20250110T023257Z
LOCATION:Hall B7 (2)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T141500
DTEND;TZID=Asia/Tokyo:20241203T151500
UID:siggraphasia_SIGGRAPH Asia 2024_sess308_IS_110@linklings.com
SUMMARY:A Quest for Building a Foundation 3D Digital Human Model
DESCRIPTION:Featured Session\n\nKoki Nagano (NVIDIA)\n\nDigital humans (DH
 ) technology has a myriad of applications, but currently each DH applicati
 on needs to train a task-specific model from scratch using a small domain-
 specific dataset (e.g., hair, body, face), which is highly inefficient and
  not scalable. In this talk, we will describe our unique approach to solvi
 ng this task by training a unified and highly photorealistic 3D foundation
  model for DH from a large collection of in-the-wild 2D data that can be u
 sed to build many different downstream applications. We will describe our 
 efforts so far on building a 3D DH foundation model and its implications f
 or the future of DH research and industry.\n\nRegistration Category: Enhan
 ced Access, Full Access, Full Access Supporter\n\nLanguage Format: English
  Language, AI Translation Multi-Language
URL:https://asia.siggraph.org/2024/program/?id=IS_110&sess=sess308
END:VEVENT
END:VCALENDAR