Key models for robotic computer vision, object grounding, 3D reconstruction, and sim-to-real transfer
-
nvidia/LocateAnything-3B
Image-Text-to-Text • 4B • Updated • 32.6k • 3.19k -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 629k • 128 -
microsoft/Florence-2-large
Image-Text-to-Text • 0.8B • Updated • 379k • 1.89k -
facebook/sam2-hiera-large
Mask Generation • 0.2B • Updated • 21.4k • 151