tum-pbs/sparse-reconstruction

Official implementation of "Guiding diffusion models to reconstruct flow fields from sparse data"

36
/ 100
Emerging

This project helps fluid dynamics researchers and engineers reconstruct complete fluid flow fields from limited measurement points. You provide sparse data, like what you'd get from a few sensors, and it generates a detailed, full-field visualization of the fluid's movement. This is for professionals working with fluid simulations, experimental fluid dynamics, or anyone analyzing complex fluid behavior.

Use this if you need to infer complete, high-resolution fluid flow patterns from sparse, incomplete measurement data.

Not ideal if you have complete, high-resolution fluid flow data and simply need to visualize it, or if you're not working with fluid dynamics.

fluid-dynamics computational-fluid-dynamics flow-reconstruction experimental-fluid-mechanics scientific-visualization
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Jupyter Notebook

License

Last pushed

Jan 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tum-pbs/sparse-reconstruction"

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