auniquesun/Point-PRC

[NeurIPS 2024] Official implementation of the paper "Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis"

47
/ 100
Emerging

This project helps researchers and engineers improve how well 3D point cloud models recognize objects, especially when faced with new object classes or different real-world conditions. It takes existing large 3D models and point cloud data, then outputs a refined model that is both highly accurate for specific tasks and more adaptable to new, unseen 3D data. This is useful for anyone working with 3D scanning, robotics, or augmented reality who needs reliable object recognition across various environments.

Use this if you are developing or deploying 3D object recognition systems and need your models to perform reliably on diverse, real-world 3D scans, not just the specific data they were trained on.

Not ideal if your application only requires object recognition on highly controlled, uniform 3D data, or if you are not working with large pre-trained 3D models.

3D-object-recognition point-cloud-analysis robotics-perception computer-vision domain-adaptation
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/auniquesun/Point-PRC"

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