BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070245Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T144000
DTEND;TZID=Australia/Melbourne:20231213T145000
UID:siggraphasia_SIGGRAPH Asia 2023_sess164_papers_155@linklings.com
SUMMARY:Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dyn
 amic Clothing Driven by Sparse RGB-D Input
DESCRIPTION:Technical Papers, TOG\n\nDonglai Xiang (Carnegie Mellon Univer
 sity/Robotics Institute, Meta Reality Labs Research); Fabian Prada, Zhe Ca
 o, Kaiwen Guo, and Chenglei Wu (Meta Reality Labs Research); Jessica Hodgi
 ns (Carnegie Mellon University); and Timur Bagautdinov (Meta Reality Labs 
 Research)\n\nClothing is an important part of human appearance but challen
 ging to model in photorealistic avatars. In this work we present avatars w
 ith dynamically moving loose clothing that can be faithfully driven by spa
 rse RGB-D inputs as well as body and face motion. We propose a Neural Iter
 ative Closest Point (N-ICP) algorithm that can efficiently track the coars
 e garment shape given sparse depth input. Given the coarse tracking result
 s, the input RGB-D images are then remapped to texel-aligned features, whi
 ch are fed into the drivable avatar models to faithfully reconstruct appea
 rance details. We evaluate our method against recent image-driven synthesi
 s baselines, and conduct a comprehensive analysis of the N-ICP algorithm. 
 We demonstrate that our method can generalize to a novel testing environme
 nt, while preserving the ability to produce high-fidelity and faithful clo
 thing dynamics and appearance.\n\nRegistration Category: Full Access\n\nSe
 ssion Chair: Parag Chaudhuri (Indian Institute of Technology Bombay)
URL:https://asia.siggraph.org/2023/full-program?id=papers_155&sess=sess164
END:VEVENT
END:VCALENDAR