vivoCameraResearch/AdaRefSR
AdaRefSR is a novel reference-based one-step diffusion super-resolution framework. Paper was accepted by ICLR2026.
This project helps you enhance low-quality images by using a high-quality reference image. You provide an image that needs improvement and a similar, clear reference image, and the system outputs a significantly sharper, more detailed version of your original image. It's designed for professionals working with visual media, such as graphic designers, photographers, or researchers who need to restore image quality.
Use this if you need to dramatically improve the resolution and detail of a low-quality image and have a high-quality reference image that depicts similar content.
Not ideal if you don't have a relevant high-quality reference image, as its performance relies heavily on effective reference utilization.
Stars
28
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vivoCameraResearch/AdaRefSR"
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