edshkim98/LocalDiffusion-Hallucination

Official code for 'Tackling Structural Hallucination in Image Translation with Local Diffusion' (ECCV'24 Oral)

19
/ 100
Experimental

When converting medical images (like MRIs or X-rays) from one style to another, this project helps prevent artificial, misleading structures from appearing in the output. It takes an input medical image and produces a translated version that accurately reflects the original data, specifically designed for medical professionals like radiologists or diagnosticians.

No commits in the last 6 months.

Use this if you need to translate medical images while maintaining high fidelity to actual patient data, avoiding "hallucinations" that could lead to misdiagnosis.

Not ideal if your primary concern is generating entirely new, unseen image content rather than accurately translating existing images.

medical-imaging radiology image-translation diagnostic-imaging medical-diagnostics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Sep 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/edshkim98/LocalDiffusion-Hallucination"

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