/AI1h ago

MAMMA Delivers Marker-Based Accuracy in Markerless 3D Motion Capture

0411366
Original post
Frank Dellaert@fdellaert#1001inAI

@Michael_J_Black This is incredible work, Michael! Amazing blend of modeling, multiview geometry, and learning. Congrats to you and the team!

Michael Black@Michael_J_Black

I’ve been capturing 3D human motion for 30 years and today is maybe the biggest day in that history. We are presenting MAMMA at CVPR (oral session 2A). MAMMA is a markerless multi-camera system that has accuracy similar to marker-based systems.

11:19 PM · Jun 7, 2026 · 57 Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS309BOOKMARKS1LIKES4RETWEETS1
Frank Dellaert@fdellaert

This paper is breathtaking! A hybrid of learning and multiview geometry with incredible motion capture results, multi-person *with* contact.

Michael Black@Michael_J_Black

I’ve been capturing 3D human motion for 30 years and today is maybe the biggest day in that history. We are presenting MAMMA at CVPR (oral session 2A). MAMMA is a markerless multi-camera system that has accuracy similar to marker-based systems.

1hViews 309Likes 4Bookmarks 1