Integrating SAM2 with DINOv2/v3 for segmentation

CLIP + DINOv3 demo with Streamlit for image similarity search

Adapting DINOv3 to downstream segmentation tasks

Object tracking using the DINOv3 model.

Classify invasive species in infrared using DINO-V3

Dinov3 exploration (use cases & capabilities )

DINOV3 Test Code (Detector)

Lightweight head for semantic segmentation using DINOv3 as backbone

Lightweight head for depth estimation using DINOv3 as backbone

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

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

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

A PyTorch implementation of an image classification system based on the DINOv3 (self-DIstillation with NO labels) vision transformer. This project provides a complete training pipeline with distributed data parallel (DDP) support, advanced data augmentation, and multiple loss functions including supervised contrastive learning.

Image classification model using DINOv3 backbone in PyTorch.

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

A image classification model trained and used.

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

unofficial JAX implementation of DINOv3, translated in full from the original Meta PyTroch reference implementation (Meta please don't sue me)

使用onnxruntime部署gazelle-dinov3凝视目标估计，包含C++和Python两个版本的程序

DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting (Neurips W4C Competition)