YunzeMan/Situation3D

[CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning

29
/ 100
Experimental

This project helps researchers working with 3D environments to improve how AI systems understand and respond to natural language questions about those spaces. It takes 3D scene data (like scans of rooms) and natural language questions, then provides a more accurate understanding of the scene from the perspective of an "embodied agent" within it. This is useful for AI researchers and engineers developing sophisticated 3D vision-language systems for tasks like robotics or virtual assistants.

No commits in the last 6 months.

Use this if you are a researcher or engineer developing AI systems that need to interpret natural language questions about 3D environments from a specific, situated viewpoint.

Not ideal if you are looking for an off-the-shelf application for end-users, or if your primary focus is on 2D image or video analysis without a 3D environmental context.

3D-vision natural-language-processing robotics-perception embodied-AI scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

43

Forks

2

Language

Python

License

MIT

Last pushed

Dec 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YunzeMan/Situation3D"

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