Robbyant/lingbot-map
Streaming 3D reconstruction via geometric context transformer
View on index · View in 3D Map
Related repos
- Vision-Language-Action foundation model for robot control
- Sparse to dense 3D reconstruction
- World simulator with real-time interactivity
- Test-time training for 3D reconstruction
- Simultaneous machine translation for live streams
- Reconstructs 3D scenes from images
- Steers Vision Transformer representations with text
- Reconstructs 3D worlds from video diffusion models
- Real-time 3D globe for coding activity
- 3D reconstruction from hand-object videos
