NVIDIA releases FoundationPose on Hugging Face: unified 6-DoF pose model, no fine-tuning needed

_akhaliq · x · 2026-09-16

NVIDIA has released FoundationPose on Hugging Face, a unified foundation model for 6-DoF object pose estimation and tracking. It works on novel objects without any fine-tuning, lowering the barrier for robotics and vision applications.

Related event: NVIDIA open-sources FoundationPose, a 6-DoF pose estimation foundation model(2 posts)→

Original post →

More from Embodied

Embodied channel →