/AI21h ago

Researcher Releases Open-Source Code For Multi-Person 3D Motion Capture

11988737.2K
Original post
Michael Black@Michael_J_Black#339inAI

Try it and capture lots of data. Let us know how it goes. MAMMA is the result of an amazing team: @Hanzcun, @soyong_shin, @TsvetelinaAlex2, @AYiannakidis, @gfgbec, Markus Höschle, Joachim Tesch & Taylor Obersat.

Michael Black@Michael_J_Black

The approach is trained on the 2-person case but generalizes well to more people interacting closely.

We make the code available for research and hope it will democratize mocap — the world needs more 3D motions. Commercial licensing is also possible.

11:01 AM · Jun 5, 2026 · 3.6K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS3.6KBOOKMARKS67LIKES73RETWEETS8REPLIES7
Michael Black@Michael_J_Black

Project: https://mamma.is.tue.mpg.de/ Code: https://github.com/cuevhv/mamma Paper: https://arxiv.org/abs/2506.13040

Michael Black@Michael_J_Black

Try it and capture lots of data. Let us know how it goes. MAMMA is the result of an amazing team: @Hanzcun, @soyong_shin, @TsvetelinaAlex2, @AYiannakidis, @gfgbec, Markus Höschle, Joachim Tesch & Taylor Obersat.

21hViews 3.6KLikes 73Bookmarks 67