# DINOv3

arXiv: https://arxiv.org/abs/2508.10104 · HTML: https://mlsanity.com/paper/2508.10104/

## Key facts

- Cited by 1,414 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2025.

## Built on by (most cited first, 30 of 1414)

- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [UniVerse-1: Unified Audio-Video Generation via Stitching of Experts](https://mlsanity.com/paper/2509.06155/) (2025)
- [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds](https://mlsanity.com/paper/2604.14268/) (2026)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [Temporal Straightening for Latent Planning](https://mlsanity.com/paper/2603.12231/) (2026)
- [TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models](https://mlsanity.com/paper/2512.02014/) (2025)
- [GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents](https://mlsanity.com/paper/2604.26752/) (2026)
- [World Models for Learning Dexterous Hand-Object Interactions from Human Videos](https://mlsanity.com/paper/2512.13644/) (2025)
- [CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos](https://mlsanity.com/paper/2601.04061/) (2026)
- [AnyUp: Universal Feature Upsampling](https://mlsanity.com/paper/2510.12764/) (2025)
- [IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction](https://mlsanity.com/paper/2510.22706/) (2025)
- [Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching](https://mlsanity.com/paper/2512.11130/) (2025)
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2509.25373/) (2025)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation](https://mlsanity.com/paper/2512.16913/) (2025)
- [JEPA-VLA: Video Predictive Embedding is Needed for VLA Models](https://mlsanity.com/paper/2602.11832/) (2026)
- [InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields](https://mlsanity.com/paper/2601.03252/) (2026)
- [Comprehensive language-image pre-training for 3D medical image understanding](https://mlsanity.com/paper/2510.15042/) (2025)
- [Emergent Outlier View Rejection in Visual Geometry Grounded Transformers](https://mlsanity.com/paper/2512.04012/) (2025)
- [E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training](https://mlsanity.com/paper/2512.10950/) (2025)

## Abstract (arXiv)

Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.