Robbyant/lingbot-vision

Pretrains self-supervised vision transformer backbones for dense spatial perception using masked boundary modeling.

View on index · View in 3D Map

Related repos

• Spatial perception via masked depth modeling
• Vision-Language-Action foundation model for robot control
• Streaming 3D reconstruction via geometric context transformer
• PyTorch computer vision toolkit with self-supervised learning, transformers, and detection models
• Unifies OpenCV and YOLOv8 into real-time perception pipeline
• PyTorch models for high-res vision tasks using self-supervised learning
• Steers Vision Transformer representations with text
• Framework for robot manipulation using vision and language models
• Toolkit for fine-tuning and training large language and vision models
• Spatial perception framework with depth sensing and tracking