TReg-inverse/TReg
Official repository for "Regularization by Texts for Latent Diffusion Inverse Solvers" (ICLR2025 spotlight)
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.
Stars
17
Forks
1
Language
Python
License
—
Category
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.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration