This code implements a NR-IQA model based on deep feature learning.
Run demo.ipynb to see how to extract deep features and train shallow regression model. To run demo.ipynb, you need to download KADID-10k database and pre-trained model from https://osf.io/xkqjh/.
Please cite the following paper if you use the code:
@inproceedings{kadid10k, title={KADID-10k: A Large-scale Artificially Distorted IQA Database}, author={Lin, Hanhe and Hosu, Vlad and Saupe, Dietmar}, booktitle={2019 Tenth International Conference on Quality of Multimedia Experience (QoMEX)}, pages={1--3}, year={2019}, organization={IEEE}}
@article{deepfl-iqa, title={DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning}, author={Lin, Hanhe and Hosu, Vlad and Saupe, Dietmar}, journal={arXiv preprint arXiv:2001.08113}, year={2020}}