Colin97/OpenShape_code

official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”

38
/ 100
Emerging

This project helps 3D designers, researchers, or anyone working with 3D models to understand and categorize shapes using natural language or images. You input 3D point cloud data, text descriptions, or images, and it outputs classifications of 3D objects (e.g., "chair," "car"), relevant 3D models based on your search, or text descriptions for point clouds. This is designed for users who need to bridge the gap between text/image queries and 3D shape data.

308 stars. No commits in the last 6 months.

Use this if you need to efficiently classify 3D shapes or retrieve 3D models from large datasets using text descriptions, images, or other 3D models.

Not ideal if your primary goal is to generate or edit detailed 3D meshes for industrial design or animation, as it focuses on semantic understanding rather than geometric manipulation.

3D-model-classification 3D-search-and-retrieval computational-design point-cloud-analysis object-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

308

Forks

21

Language

Python

License

Apache-2.0

Last pushed

Mar 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Colin97/OpenShape_code"

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