CVMI-Lab/PLA

(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

36
/ 100
Emerging

This project helps computer vision researchers and AI developers analyze 3D scene data more effectively. By inputting 3D point cloud scans and descriptive text, it outputs detailed understandings of objects and regions within the scene, even for objects not seen during training. This allows for flexible and open-ended scene interpretation.

298 stars. No commits in the last 6 months.

Use this if you need to build or research AI systems that understand complex 3D environments using both visual data and natural language descriptions, especially for tasks requiring recognition of novel objects.

Not ideal if you are looking for a plug-and-play application for end-users, as this is a research-focused implementation requiring technical expertise to set up and run.

3D-computer-vision scene-understanding AI-research robotics spatial-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

298

Forks

12

Language

Python

License

Apache-2.0

Last pushed

Jun 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/CVMI-Lab/PLA"

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