All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

[DEIMv2] Real Time Object Detection Meets DINOv3

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.

A repository to apply DINOv3 models for different downstream tasks: image classification, semantic segmentation, object detection.

Integrating SAM2 with DINOv2/v3 for segmentation

Command-line tool for extracting DINOv3, CLIP, SigLIP2, RADIO, features for images and videos

dinov3例子

Switch the backbone of mask2former to DINOv3 for instance segmentation

Adapting DINOv3 to downstream segmentation tasks

The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

Lightweight head for depth estimation using DINOv3 as backbone

Lightweight head for object detection using DINOv3 as backbone

Open-source desktop app for AI-powered animal behavior analysis. v3 (beta) is actively developed and recommended for new projects. For published, reproducible code, use v2-stable.

[DEIMv2] Real Time Object Detection Meets DINOv3 C++ and ONNX version

Dinov3 exploration (use cases & capabilities )

CLIP + DINOv3 demo with Streamlit for image similarity search

Gaze-LLE-DINOv3: Gaze Target Estimation via Large-Scale Learned Encoders with DINOv3

A set of tools and examples for converting and utilizing powerful vision models, DINOv3 and EdgeTAM (SAM2), within the ONNX ecosystem.

Object tracking using the DINOv3 model.