What is it about?
We propose the first real-time full motion capture technique that simultaneously estimates human poses and global translations using only six inertial measurement units at over 90 fps. Our system can capture the full motions of the subjects faithfully regardless of occlusion, environment, or multi-person ambiguities, with state-of-the-art accuracy and smoothness.
Featured Image
Photo by Ryan Garry on Unsplash
Read the Original
This page is a summary of: TransPose, ACM Transactions on Graphics, August 2021, ACM (Association for Computing Machinery), DOI: 10.1145/3450626.3459786.
You can read the full text:
Contributors
The following have contributed to this page