milad1378yz/MOTFM

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

50
/ 100
Established

Implements optimal transport-based flow matching with PyTorch Lightning and MONAI generative models, enabling both 2D/3D synthesis and dual mask/class conditioning. The framework uses configurable ODE solvers with adjustable inference steps and includes built-in 3D evaluation metrics (MMD, MS-SSIM, 3D-FID). Data must be prepared as a single pickled dictionary with image/mask/class splits, with inference outputs supporting multiple normalization strategies and checkpoint resolution patterns.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

64

Forks

8

Language

Python

License

MIT

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/milad1378yz/MOTFM"

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