FlowDPS-Inverse/FlowDPS

[ICCV2025] Official repository of "FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems"

25
/ 100
Experimental

This project helps image processing specialists and researchers reconstruct high-quality images from degraded versions. You provide a low-resolution, blurred, or noisy image, and it outputs a clearer, sharper, and higher-resolution image. It's designed for anyone working with image restoration from various types of damage or limitations.

No commits in the last 6 months.

Use this if you need to restore or enhance images that have been degraded by processes like super-resolution downsampling or motion blur, especially for tasks involving faces or animals.

Not ideal if your primary goal is to generate entirely new images from scratch or if you require real-time processing on very large batches of diverse image types without prior domain adaptation.

image-restoration super-resolution deblurring computational-photography image-enhancement
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

58

Forks

3

Language

Python

License

Last pushed

Jul 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FlowDPS-Inverse/FlowDPS"

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