https://github.com/celuigi/biqa4consumerphotographs
Source code for the paper "Blind Image Quality Assessment of Authentically Distorted Images"
https://github.com/celuigi/biqa4consumerphotographs
authentically-distorted-images biqa consumer-photographs convolutional-neural-networks deep-learning image-quality-assessment machine-learning no-reference nr-iqa pytorch
Last synced: 24 days ago
JSON representation
Source code for the paper "Blind Image Quality Assessment of Authentically Distorted Images"
- Host: GitHub
- URL: https://github.com/celuigi/biqa4consumerphotographs
- Owner: CeLuigi
- Created: 2021-10-28T18:17:34.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-03-02T09:01:06.000Z (over 4 years ago)
- Last Synced: 2025-02-23T02:38:09.400Z (over 1 year ago)
- Topics: authentically-distorted-images, biqa, consumer-photographs, convolutional-neural-networks, deep-learning, image-quality-assessment, machine-learning, no-reference, nr-iqa, pytorch
- Homepage:
- Size: 3.04 MB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Blind Image Quality Assessment of Authentically Distorted Images
Code for the paper *Blind Image Quality Assessment of Authentically Distorted Images* ([JOSA A](https://doi.org/10.1364/JOSAA.448144)).
## Proposed architecture

## Dependencies
* Python 3.8
* [PyTorch](https://pytorch.org/) 1.5.1
* Torchvision
* Cuda 11.4
## Reference
If you have any question, please do not hesitate to contact luigi.celona@unimib.it
If you find this code useful to your research, please consider citing:
* Luigi Celona, and Raimondo Schettini. Blind Image Quality Assessment of Authentically Distorted Images. In _JOSA A_, _volume 39_, _number 4_, pp. -, 2022.
```
@article{celona2022blind,
author = {Celona, Luigi and Schettini, Raimondo},
title = {Blind Quality Assessment of Authentically Distorted Images},
journal = {Journal of the Optical Society of America A},
volume = {39},
year = {2022},
number = {4},
pages = {B1--B10},
doi = {10.1364/JOSAA.448144}
}
```