pengsongyou/openscene

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

43
/ 100
Emerging

This project helps anyone working with 3D environment scans to quickly identify and highlight specific objects, materials, properties, or even abstract concepts within those scans. You provide a 3D scan or depth data, type in a descriptive phrase like "festive" or "made of metal," and the system highlights the corresponding regions. This is ideal for professionals in fields like architecture, interior design, robotics, or virtual reality development who need to understand and interact with 3D scene data.

800 stars. No commits in the last 6 months.

Use this if you need to perform real-time, interactive searches within complex 3D scans using natural language descriptions, even for rare objects or abstract ideas.

Not ideal if your primary goal is standard object detection with a fixed, predefined list of categories or if you don't work with 3D scene data.

3D scene analysis augmented reality robotics navigation virtual environment design spatial intelligence
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

800

Forks

65

Language

Python

License

Apache-2.0

Last pushed

Oct 27, 2023

Commits (30d)

0

Get this data via API

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

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