WebAR-rocks/WebAR.rocks.train

Object detection, tracking, and 6DoF pose estimation in the web browser, integrated training environment to train your own neural network models 🚀

41
/ 100
Emerging

This tool helps augmented reality (AR) developers and designers create custom AR experiences by training neural networks to recognize and track specific real-world objects in a web browser. You provide 3D models of objects, and it outputs a trained neural network model. This model can then be used to build AR applications where virtual content interacts seamlessly with the detected objects.

Use this if you need to train custom object detection and 6DoF pose estimation models for web-based augmented reality applications without needing to install complex machine learning frameworks.

Not ideal if you need a general-purpose machine learning framework for tasks other than object detection and tracking for AR, or if you prefer a traditional Python-based development environment.

augmented-reality web-development 3D-modeling object-tracking digital-experiences
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

99

Forks

7

Language

JavaScript

License

MIT

Last pushed

Dec 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/WebAR-rocks/WebAR.rocks.train"

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