bowang-lab/MedSAM2
Segments objects in 3D medical images and videos
View on index · View in 3D Map
Related repos
- Multi-agent framework for chest X-ray interpretation
- 3D reconstruction from monocular endoscopic video
- 3D markerless kinematics from 2D videos
- Reconstructs 3D humans from photo collections without tuning
- Person and body-part segmentation model
- Generates 3D shapes from images or text
- Generates videos with consistency across shots
- image-to-3D matching with MASt3R
- Geometric 3D vision from images
- Reconstructs 4D human scenes from videos
