[DEIMv2] Real Time Object Detection Meets DINOv3
- Updated
Mar 24, 2026 - Jupyter Notebook
#
dinov3
Here are 68 public repositories matching this topic...
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
python machine-learning real-time computer-vision deep-learning pytorch embeddings yolo object-detection pretrained-models semantic-segmentation self-supervised distillation self-supervised-learning contrastive-learning vision-transformer dinov2 rtdetrv2 eomt dinov3
- Updated
Mar 25, 2026 - Python
Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)
- Updated
Oct 24, 2025 - Jupyter Notebook
SimpleAICV:pytorch training examples.
sam pytorch resnet vit van retinanet yolact fcos detr solov2 segment-anything sam2 segment-anything-2 convformer dinov3
- Updated
Mar 21, 2026 - Python
A repository to apply DINOv3 models for different downstream tasks: image classification, semantic segmentation, object detection.
- Updated
Oct 14, 2025 - Python
ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
computer-vision deep-learning robotics pytorch object-detection optical-flow semantic-segmentation depth-estimation ros2 multi-task-learning visual-perception dinov3
- Updated
Oct 21, 2025 - Python
Integrating SAM2 with DINOv2/v3 for segmentation
- Updated
Aug 8, 2025 - Python
Command-line tool for extracting DINOv3, CLIP, SigLIP2, RADIO, features for images and videos
- Updated
Feb 28, 2026 - Python
Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"
lightweight real-time computer-vision object-detection pose-estimation instance-segmentation distillation dinov3
- Updated
Mar 25, 2026 - Python
Switch the backbone of mask2former to DINOv3 for instance segmentation
- Updated
Mar 24, 2026 - Python
[CVPR'26] Official Code for “V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence”
- Updated
Mar 22, 2026 - Python
[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
machine-learning computer-vision representation-learning anomalydetection clip anomaly-detection few-shot-learning anomaly-detection-algorithm anomaly-segmentation anomaly-localization foundation-models dinov2 few-shot-anomaly-detection siglip dinov3
- Updated
Mar 16, 2026 - Python
[DEIMv2] Real Time Object Detection Meets DINOv3 C++ and ONNX version
- Updated
Dec 31, 2025 - C++
DeepStream integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
computer-vision deep-learning cpp robotics cuda object-detection deepstream optical-flow semantic-segmentation depth-estimation multi-task-learning visual-perception dinov3
- Updated
Feb 5, 2026 - C++
unofficial JAX implementation of DINOv3, translated in full from the original Meta PyTroch reference implementation (Meta please don't sue me)
- Updated
Nov 11, 2025 - Python
Lightweight head for depth estimation using DINOv3 as backbone
- Updated
Oct 11, 2025 - Python
Improve this page
Add a description, image, and links to the dinov3 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the dinov3 topic, visit your repo's landing page and select "manage topics."