DINOv3
One frozen backbone, from Instagram photos to Mars
Latest: DINOv3 (Aug 14, 2025)
Meta's flagship self-supervised backbone, released August 14, 2025: a 7B-parameter ViT trained on 1.7B images with no labels, plus distilled ViT-B/ViT-L and ConvNeXt variants, all under a commercial-use license. Produces state-of-the-art dense features for detection, segmentation, and depth — including a dedicated satellite-imagery model trained on 493M Maxar tiles.
Why it matters
DINOv3 scaled self-supervised vision to a 7B ViT trained on 1.7B images with no labels, producing dense features that beat specialist models on segmentation and depth while frozen. A satellite variant cut tree-canopy-height error in Kenya from 4.1m to 1.2m, and it now underpins SAM 3D Body and WRI deforestation monitoring.
Facts
- A single frozen vision model that works from Instagram photos to satellite passes over the Amazon.
- The World Resources Institute uses DINOv3 to monitor deforestation — its satellite variant cut tree-canopy-height error in a Kenyan region from 4.1m to 1.2m vs DINOv2 — and NASA's Jet Propulsion Laboratory uses DINO models for Mars robotics.
- SAM 3D Body is built on a DINOv3 backbone.
- Frozen backbone, no labels, no fine-tuning — yet it beats specialist models on dense tasks like segmentation and depth.
- Trained on roughly 1.7B images with a 67-page report and 26 authors (Siméoni et al.).
Try it yourself
dinov3-vitb16 on Hugging Face ↗ Full DINOv3 collection on Hugging Face ↗ Run the PCA-features notebook in Colab ↗
Lineage
Sources
arXiv ↗GitHub · dinov3 ↗Meta AI blog ↗