New protocols show depth bias at 5m varies from 50mm to over 1400mm across five cameras, with 3D pose error (MPJPE 104-365mm) tracking depth quality while 2D pose accuracy remains comparable (78-90% mAP).
Pierce, Daniel K
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Evaluation of three pose estimation methods on infant videos shows Sapiens best for 2D consistency and SAM 3D Body best for 3D kinematic reconstruction with 19-28 mm errors, plus proof-of-concept for distinguishing motor patterns.
citing papers explorer
-
Evaluation Protocols and Validation for Cameras in Indoor Healthcare Monitoring
New protocols show depth bias at 5m varies from 50mm to over 1400mm across five cameras, with 3D pose error (MPJPE 104-365mm) tracking depth quality while 2D pose accuracy remains comparable (78-90% mAP).
-
Markerless Motion Capture for Biomechanical Whole-Body Kinematic Estimation in Infants
Evaluation of three pose estimation methods on infant videos shows Sapiens best for 2D consistency and SAM 3D Body best for 3D kinematic reconstruction with 19-28 mm errors, plus proof-of-concept for distinguishing motor patterns.