Raessan/depth_dinov3

Lightweight head for depth estimation using DINOv3 as backbone

23
/ 100
Experimental

This project helps roboticists and computer vision engineers add depth perception to their systems. It takes a standard camera image as input and outputs a detailed depth map, showing how far away objects are. This tool is designed for developers working with robotics platforms like ROS 2 to integrate real-time 3D understanding into their applications.

No commits in the last 6 months.

Use this if you need to equip a robotic system or vision application with real-time, accurate depth estimation from camera feeds, especially when using the DINOv3 visual backbone.

Not ideal if you're looking for a general-purpose image processing library that doesn't focus on real-time depth estimation or integration with ROS 2.

robotics computer-vision depth-sensing perception ROS-2
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

Apache-2.0

Last pushed

Oct 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Raessan/depth_dinov3"

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