Robbyant/lingbot-depth
Spatial perception via masked depth modeling
View on index · View in 3D Map
Related repos
- Vision-Language-Action foundation model for robot control
- Streaming 3D reconstruction via geometric context transformer
- Causal world modeling for robot control
- World simulator with real-time interactivity
- Spatial perception framework with depth sensing and tracking
- Framework for robot manipulation using vision and language models
- ERNIE by PaddlePaddle—models, toolkits, and workflows for training and inference with language and vision tasks
- Predicts geometry from visual inputs without camera poses
- Tracks faces and bodies in 3D using computer vision
- Robot vision framework with world models for edge devices
