facebookresearch/dinov3
Reference PyTorch implementation and models for DINOv3
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #79 among AI repositories tracked this week, and #79 over the last 30 days; #654 of 2,794 repositories GStars tracks this week (top 23%).
The project lists 13 contributors on GitHub.
Gained 24% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides reference PyTorch implementations and pretrained models for DINOv3, a vision foundation model producing high-quality dense image features.
- Delivers versatile pretrained backbones and heads that outperform specialized state-of-the-art vision models without fine-tuning across diverse tasks.
- Use for extracting dense visual features and embeddings for image understanding tasks using pretrained ViT and ConvNeXt backbones.
- Use for zero-shot and supervised image segmentation, detection, and depth estimation leveraging pretrained heads on ADE20K, COCO2017, and SYNTHMIX datasets.
- Use for research and development in self-supervised vision models, enabling experiments with open-vocabulary segmentation and video segmentation tracking.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
🆕 [2025-09-17] :fire: DINOv3 backbones are now supported by the PyTorch Image Models / timm library starting with version 1.0.20
[2025-08-29] DINOv3 backbones are supported by released versions of the Hugging Face Transformers library starting with version 4.56.0
[2025-08-14] DINOv3 backbones are now available in Hugging Face Hub and supported by the development version of the Hugging Face Transformers library
Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab,
Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa,
Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang,
Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts,
Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie,
Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
976+66
Open issues
167+16
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| storytold/artcraft | 35.6K | +6.7K | 75 | 26 days ago |
| heygen-com/hyperframes | 70.0K | +5.7K | 45 | today |
| Comfy-Org/ComfyUI | 142.0K | +4.4K | 60 | 3 days ago |
| Leonxlnx/taste-skill | 101.1K | +4.0K | 75 | 2 days ago |
| ifixai-ai/iFixAi | 30.7K | +3.3K | 75 | 5 days ago |
| facebookresearch/dinov3 | 11.6K | +0 | 75 | — |
| Category median | 70.0K | +4.4K | 75 | — |
Also by facebookresearch
Other repositories from this maintainer that GStars tracks
- Python34.9K stars
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
- Python14.5K stars
vggt
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
- Python12.1K stars
sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
- Python10.6K stars
xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
- Python4.8K stars
vjepa2
PyTorch code and models for VJEPA2 self-supervised learning from video.
Discover Repositories
Search across tracked repositories by name or description