facebookresearch/dinov3
PyTorch models for high-res vision tasks using self-supervised learning
View on index · View in 3D Map
Related repos
- Library for video understanding research
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- Reconstructs 3D scenes from 1000+ images in one forward pass
- Unified vision model for open-world object detection
- PyTorch computer vision toolkit with self-supervised learning, transformers, and detection models
- Open vision-language models that compete with closed-source alternatives using fully open data
- video and image watermarking code for training and inference
- Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
- State-of-the-art object detection and segmentation library from Facebook AI Research
- Collection of PyTorch image models, training scripts, and utilities
