facebookresearch/dinov3
Vision foundation models for dense features
View on index · View in 3D Map
Related repos
- Infers 3D scene attributes from views
- Reconstructs 3D scenes from 1000+ images in one forward pass
- Unified vision model for open-world object detection
- Generates 3D meshes from image sequences and SLAM points
- Regress metric 3D geometry from images via transformers
- Model for reconstruction of 3D objects from images
- Open vision-language models that compete with closed-source alternatives using fully open data
- video and image watermarking code for training and inference
- Library for object detection and segmentation
