Immensely proud to have been part of this project. Thank you to the team: @oriane_simeoni, @huyvvo, @baldassarrefe.bsky.social, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michael Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, …

And here’s my favorite figure from the paper, showing high resolution DINOv3 representations in all their detail-capturing glory ✨

To recap:

1) The promise of SSL is finally realized, enabling foundation models across domains
2) High quality dense features enabling SotA applications
3) A versatile family of models for diverse deploy scenarios

So many great ideas (Gram anchoring!) to how we got there, please read the paper!

Satellite you said? Yes, the same DINOv3 algorithm trained on satellite imagery produces a SotA model for geospatial tasks like canopy height estimation. And of course, learns beautiful feature maps. This is the magic of SSL 🪄

3) DINOv3 is a family of models covering all use cases:

• ViT-7B flagship model
• ViT-S/S+/B/L/H+ (21M-840M params)
• ConvNeXt variants for efficient inference
• Text-aligned ViT-L (dino.txt)
• ViT-L/7B for satellite

All inheriting the great dense features of the 7B!

Well, Jianyuan Wang of VGGT fame simply dropped DINOv3 into his pipeline and off-handedly got a new SotA 3D model out. Seems promising enough?

2) DINOv3’s global understanding is strong, but its dense representations truly shine! There’s a clear gap between DINOv3 and prior methods across many tasks. This matters as pretrained dense features power many applications: MLLMs, video&3D understanding, robotics, generative models, …

1) Some history: on ImageNet classification, supervised and weakly-supervised models converged to the same plateau over the last years. With DINOv3, SSL finally reaches that level. This alone is a big deal: no more reliance on annotated data!

Introducing DINOv3 🦕🦕🦕

A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale.
High quality dense features, combining unprecedented semantic and geometric scene understanding.

Three reasons why this matters👇