emg2pose: Surface EMG and Hand Pose
This dataset is a NEMAR re-host and EMG-BIDS conversion of the public emg2pose release from Meta Reality Labs. It contains 2 kHz, 16-channel wrist surface electromyography recordings paired with hand pose labels (joint angles) captured by a 26-camera motion-capture system. The release spans 193 users, 370 hours, and 29 behavioral stages, supporting benchmarking of sEMG-based hand pose estimation.
- Participants
- 193
- Size
- 740 GB
- Version
- vv1.0.5
- Updated
- Nov 1, 2026