um-dsrg/RUMpy
Open source image super-resolution toolbox containing various functionality for training a diverse number of state-of-the-art deep learning models. Also acts as the companion code for the MDPI Sensors journal paper titled 'The Best of Both Worlds: A Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks'
This project helps researchers and practitioners in computer vision enhance low-resolution images or video frames. It takes in existing high-resolution image datasets, adds various types of realistic degradation like blurring and noise, and then trains or fine-tunes advanced deep learning models to reconstruct a clear, high-resolution image from a degraded input. Users include computer vision scientists, imaging specialists, and machine learning researchers working on image quality improvement.
No commits in the last 6 months.
Use this if you need to perform blind image super-resolution, meaning you want to upscale images without knowing the exact degradation process, and you need a flexible toolbox to experiment with state-of-the-art deep learning models.
Not ideal if you're looking for a simple, off-the-shelf image upscaler without needing to train custom models or dive into deep learning architectures.
Stars
29
Forks
1
Language
Python
License
GPL-3.0
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/um-dsrg/RUMpy"
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