CUHK-AIM-Group/Polyp-Gen
[ICRA 2025] Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion
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.
Stars
24
Forks
3
Language
Python
License
—
Category
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.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...