Raessan/object_detection_dinov3

Lightweight head for object detection using DINOv3 as backbone

33
/ 100
Emerging

This project helps robotics engineers and perception system developers integrate real-time object detection into their ROS 2 applications. It takes raw image data, processes it using a specialized detection head on top of DINOv3 features, and outputs bounding box predictions for objects within the image. This allows for efficient and accurate object recognition in live robotic environments.

Use this if you need a lightweight and efficient object detection solution that can be integrated into a ROS 2 system, leveraging existing DINOv3 backbone features for real-time performance.

Not ideal if you are looking for a standalone, state-of-the-art object detection model that does not specifically target integration with DINOv3 or ROS 2.

robotics computer-vision ROS-2 perception-systems real-time-processing
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Jan 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Raessan/object_detection_dinov3"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.