jayliu0313/Diffusion_Multi-View_AD

Learning Diffusion Models for Multi-View Anomaly Detection [ECCV2024]

14
/ 100
Experimental

This project helps engineers or quality control specialists identify unusual defects in products or components viewed from multiple angles. It takes a collection of multi-view images of items (some normal, some potentially flawed) and processes them to highlight areas that deviate from expected patterns, generating visual heatmaps that pinpoint anomalies. This tool is designed for anyone responsible for automated visual inspection in manufacturing or production.

No commits in the last 6 months.

Use this if you need to automatically detect subtle or complex anomalies in industrial products that are captured using multiple camera views.

Not ideal if you are looking for an out-of-the-box solution with a graphical user interface, as this requires command-line execution and dataset preparation.

quality-control industrial-inspection defect-detection manufacturing computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

Last pushed

Oct 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jayliu0313/Diffusion_Multi-View_AD"

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