CUHK-AIM-Group/Polyp-Gen

[ICRA 2025] Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion

34
/ 100
Emerging

This project helps medical researchers and developers working on endoscopic image analysis by generating new, realistic, and diverse polyp images. You provide existing endoscopic images, optionally with specified polyp masks, and it creates synthetic images of polyps in various clinical settings. This is useful for expanding datasets to train machine learning models for polyp detection.

Use this if you need to create a larger, more varied dataset of endoscopic images featuring polyps to improve the training of your medical image analysis models, especially when real data is scarce or limited in diversity.

Not ideal if you are looking to diagnose polyps directly or if you need to generate entirely new anatomical structures rather than variations of existing polyp images.

endoscopy medical-imaging polyp-detection dataset-expansion gastroenterology
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

24

Forks

3

Language

Python

License

Last pushed

Feb 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CUHK-AIM-Group/Polyp-Gen"

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