jayliu0313/Shape-Guided

Shape-Guided Dual-Memory Learning for 3D Anomaly Detection [ICML2023]

29
/ 100
Experimental

This project helps quality control engineers and manufacturing inspectors automatically identify defects or anomalies on the surface of 3D objects. It takes in 3D point cloud data and corresponding RGB images of an object, then outputs a score map highlighting potential anomalies. This is ideal for professionals tasked with visually inspecting objects for imperfections.

No commits in the last 6 months.

Use this if you need to reliably detect unusual features or defects on the surface of manufactured parts or scanned objects using both their visual appearance and 3D shape information.

Not ideal if you are working with 2D images only or need to analyze internal structures rather than surface anomalies.

quality-inspection manufacturing-defect-detection 3d-scanning industrial-automation surface-anomaly-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

48

Forks

7

Language

Python

License

Last pushed

Oct 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jayliu0313/Shape-Guided"

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