TReg-inverse/TReg

Official repository for "Regularization by Texts for Latent Diffusion Inverse Solvers" (ICLR2025 spotlight)

19
/ 100
Experimental

This project helps you reconstruct clearer, more accurate images from degraded inputs like blurry photos or low-resolution scans. You provide a corrupted image and a text description of what the final image should depict. The system then generates a restored image that not only looks better but also aligns with your provided text, offering more precise control over the output. Anyone working with image restoration, like forensic specialists, archival technicians, or visual content creators, could use this.

No commits in the last 6 months.

Use this if you need to restore degraded images and want to guide the restoration process with specific text descriptions to achieve a desired outcome.

Not ideal if you are looking for a fully automated image restoration tool without any text-based input or if you only need basic image enhancement without semantic guidance.

image-restoration digital-forensics photo-enhancement visual-content-creation archival-imaging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Python

License

Last pushed

Mar 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TReg-inverse/TReg"

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