Key models for robotic computer vision, object grounding, 3D reconstruction, and sim-to-real transfer
-
nvidia/LocateAnything-3B
Image-Text-to-Text • 4B • Updated • 89.4k • 3.04k -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 856k • 119 -
microsoft/Florence-2-large
Image-Text-to-Text • 0.8B • Updated • 543k • 1.86k -
facebook/sam2-hiera-large
Mask Generation • 0.2B • Updated • 16.3k • 141