( 03 )Layer

MoCap Kinematics

Millimetre

Optical and inertial full-body and hand kinematics, aligned frame-for-frame to the egocentric view.

Captured during real manipulation rather than in a studio reproduction, and aligned frame-for-frame to the egocentric and multi-view footage of the same take.

Use it as ground truth for hand-pose accuracy, or as a direct kinematic source for retargeting onto a target embodiment.

Like 4D, this requires a controlled, instrumented site — not a head-mounted phone.

SPECIFICATION
System
Optical + inertial fusion
Body
Full-body skeleton, per-joint
Hand
Per-finger, per-joint
Alignment
Frame-for-frame to ego view

Available on MOVAS-Ego 100K. Coverage per scene family is published on each family page and on the data card.

FAQ

MoCap Kinematics — Common Questions

No. It is available for the instrumented subset of each scene family, and coverage is stated on every scene-family page and on the data card. We publish the real number rather than an average.

Your models need the physical world.

Start with training-ready data today. Scale to targeted re-capture when you’re ready.

Request a Subset

Data moves robots. MOVAS moves data.