Signed in
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
| No holders yet. | ||||||||||
Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks.