BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_589@linklings.com
SUMMARY:Transformer Inertial Poser: Real-time Human Motion Reconstruction 
 from Sparse IMUs with Simultaneous Terrain Generation
DESCRIPTION:Technical Papers\n\nTransformer Inertial Poser: Real-time Huma
 n Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generat
 ion\n\nJiang, Ye, Gopinath, Won, Winkler...\n\nReal-time human motion reco
 nstruction from a sparse set of (e.g. six) wearable IMUs provides a non-in
 trusive and economic approach to motion capture. Without the ability to ac
 quire position information directly from IMUs, recent works took data-driv
 en approaches that utilize large human motion datasets to tackle this unde
 r-determined problem. Still, challenges remain such as temporal consistenc
 y, drifting of global and joint motions, and diverse coverage of motion ty
 pes on various terrains. We propose a novel method to simultaneously estim
 ate full-body motion and generate plausible visited terrain from only six 
 IMU sensors in real-time. Our method incorporates 1. a conditional Transfo
 rmer decoder model giving consistent predictions by explicitly reasoning p
 rediction history, 2. a simple yet general learning target named "stationa
 ry body points” (SBPs) which can be stably predicted by the Transformer mo
 del and utilized by analytical routines to correct joint and global drifti
 ng, and 3. an algorithm to generate regularized terrain height maps from n
 oisy SBP predictions which can in turn correct noisy global motion estimat
 ion. We evaluate our framework extensively on synthesized and real IMU dat
 a, and with real-time live demos, and show superior performance over stron
 g baseline methods.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS
  ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat
 : IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_589&sess=sess15
 3
END:VEVENT
END:VCALENDAR