cszn/SRMD
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)
This project enhances the quality of low-resolution images by recovering fine details, even when they're blurry or noisy from various sources. It takes a degraded image along with information about its blur and noise levels, then outputs a clearer, higher-resolution version. Image analysts, forensic specialists, or anyone needing to improve image clarity for inspection or presentation would use this.
433 stars. No commits in the last 6 months.
Use this if you need to upscale poor-quality images that suffer from different types of blur and noise, and you know the degradation parameters like blur kernel and noise level.
Not ideal if you have perfect, clean low-resolution images that only need simple bicubic upscaling without complex degradation recovery.
Stars
433
Forks
80
Language
MATLAB
License
—
Category
Last pushed
Oct 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cszn/SRMD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HasnainRaz/Fast-SRGAN
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
NatLabRockies/sup3r
The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial...
the-database/traiNNer-redux
Deep learning training framework for image super resolution and restoration.
eugenesiow/super-image
Image super resolution models for PyTorch.
movehand/raisr
A Python implementation of RAISR