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:20260114T163643Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T154500
DTEND;TZID=Australia/Melbourne:20231214T155500
UID:siggraphasia_SIGGRAPH Asia 2023_sess158_papers_239@linklings.com
SUMMARY:Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views
DESCRIPTION:Taeho Kang and Kyungjin Lee (Seoul National University), Jinru
 i Zhang (Central South University), and Youngki Lee (Seoul National Univer
 sity)\n\nWe present Ego3DPose, a highly accurate binocular egocentric 3D p
 ose reconstruction system. The binocular egocentric setup offers practical
 ity and usefulness in various applications, however, it remains largely un
 der-explored. It has been suffering from low pose estimation accuracy due 
 to viewing distortion, severe self-occlusion, and limited field-of-view of
  the joints in egocentric 2D images. Here, we notice that two important 3D
  cues, stereo correspondences, and perspective, contained in the egocentri
 c binocular input are neglected. Current methods heavily rely on 2D image 
 features, implicitly learning 3D information, which introduces biases towa
 rds commonly observed motions and leads to low overall accuracy. We observ
 e that they not only fail in challenging occlusion cases but also in estim
 ating visible joint positions. To address these challenges, we propose two
  novel approaches. First, we design a two-path network architecture with a
  new path that estimates pose per limb independently. It learns to output 
 the 3D orientation of each limb with confidence based on the specific limb
 ’s heatmaps from a stereo view. It does not rely on full-body information 
 and alleviates bias toward learned full-body poses. Second, we leverage th
 e egocentric view of body limbs, which exhibits strong perspective varianc
 e (e.g., a significantly large-size hand when it is close to the camera). 
 We propose a new perspective-aware representation using trigonometry, enab
 ling the network to estimate the 3D orientation of limbs. Finally, we deve
 lop an end-to-end pose reconstruction network that synergizes both techniq
 ues. Our comprehensive evaluations demonstrate that Ego3DPose outperforms 
 state-of-the-art models by a pose estimation error (i.e., MPJPE) reduction
  of 23.1% in the UnrealEgo dataset. Our qualitative results highlight the 
 superiority of our approach across a range of scenarios and challenges\n\n
 Registration Category: Full Access\n\nSession Chair: Jae-Ho Nah (Sangmyung
  University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_239&sess=sess158
END:VEVENT
END:VCALENDAR