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:20260817T171532Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T111900
DTEND;TZID=Asia/Tokyo:20241205T113100
UID:siggraphasia_SIGGRAPH Asia 2024_sess129_papers_231@linklings.com
SUMMARY:Look Ma, no markers: holistic performance capture without the hass
 le
DESCRIPTION:Charlie Hewitt, Fatemeh Saleh, Sadegh Aliakbarian, Lohit Petik
 am, Shideh Rezaeifar, Louis Florentin, Zafiirah Hosenie, Thomas J. Cashman
 , and Julien Valentin (Microsoft); Darren Cosker (Microsoft, University of
  Bath); and Tadas Baltrusaitis (Microsoft)\n\nWe tackle the problem of hig
 hly-accurate, holistic performance capture for the face, body and hands si
 multaneously. Motion-capture technologies used in film and game production
  typically focus only on face, body or hand capture independently, involve
  complex and expensive hardware and a high degree of manual intervention f
 rom skilled operators. While machine-learning-based approaches exist to ov
 ercome these problems, they usually only support a single camera, often op
 erate on a single part of the body, do not produce precise world-space res
 ults, and rarely generalize outside specific contexts. In this work, we in
 troduce the first technique for marker-free, high-quality reconstruction o
 f the complete human body, including eyes and tongue, without requiring an
 y calibration, manual intervention or custom hardware. Our approach produc
 es stable world-space results from arbitrary camera rigs as well as suppor
 ting varied capture environments and clothing. We achieve this through a h
 ybrid approach that leverages machine learning models trained exclusively 
 on synthetic data and powerful parametric models of human shape and motion
 . We evaluate our method on a number of body, face and hand reconstruction
  benchmarks and demonstrate state-of-the-art results that generalize on di
 verse datasets.\n\nRegistration Category: Full Access, Full Access Support
 er\n\nLanguage Format: English Language\n\nSession Chair: Yuting Ye (Reali
 ty Labs Research, Meta; Meta)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_231&sess=sess129
END:VEVENT
END:VCALENDAR