aofrancani/DPT-VO

Dense Prediction Transformer for scale estimation in monocular visual odometry

35
/ 100
Emerging

When navigating with a single camera, such as on an autonomous vehicle or a medical robot, it's hard to precisely know your exact distance or scale from objects. This project takes a sequence of single-camera images and outputs improved depth and position estimates, making your robot's or device's movements more accurate. This is for robotics engineers or developers working on monocular visual odometry systems.

No commits in the last 6 months.

Use this if you need to improve the accuracy of scale and depth estimation in monocular visual odometry systems for applications like autonomous navigation or augmented reality.

Not ideal if you are working with stereo cameras, LiDAR, or other depth-sensing technologies, as this project specifically addresses single-camera scale ambiguity.

robotics autonomous-navigation computer-vision visual-odometry depth-estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Python

License

MIT

Last pushed

Dec 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/aofrancani/DPT-VO"

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