This repository contains a unified interface for downloading and loading 20 popular Image Quality Assessment (IQA) datasets. We provide codes for both general Python and PyTorch.
This repository is part of our Bayesian IQA project where we present an overview of IQA methods from a Bayesian perspective. More detailed summaries of both IQA models and datasets can be found in this interactive webpage.
If you find our project useful, please cite our paper
@article{duanmu2021biqa,
author = {Duanmu, Zhengfang and Liu, Wentao and Wang, Zhongling and Wang, Zhou},
title = {Quantifying Visual Image Quality: A Bayesian View},
journal = {Annual Review of Vision Science},
volume = {7},
number = {1},
pages = {437-464},
year = {2021}
}
Dataset | Dis Img | Ref Img | MOS | DMOS |
---|---|---|---|---|
LIVE | ✔️ | ✔️ | ✔️ | |
A57 | ✔️ | ✔️ | ✔️ | |
LIVE_MD | ✔️ | ✔️ | ✔️ | |
MDID2013 | ✔️ | ✔️ | ✔️ | |
CSIQ | ✔️ | ✔️ | ✔️ | |
KADID-10k | ✔️ | ✔️ | ✔️(Note) ~~~~ | |
TID2008 | ✔️ | ✔️ | ✔️ | |
TID2013 | ✔️ | ✔️ | ✔️ | |
CIDIQ_MOS100 | ✔️ | ✔️ | ✔️ | |
CIDIQ_MOS50 | ✔️ | ✔️ | ✔️ | |
MDID2016 | ✔️ | ✔️ | ✔️ | |
SDIVL | ✔️ | ✔️ | ✔️ | |
MDIVL | ✔️ | ✔️ | ✔️ | |
Toyama | ✔️ | ✔️ | ✔️ | |
PDAP-HDDS | ✔️ | ✔️ | ✔️ | |
VCLFER | ✔️ | ✔️ | ✔️ | |
LIVE_Challenge | ✔️ | ✔️ | ||
CID2013 | ✔️ | ✔️ | ||
KonIQ-10k | ✔️ | ✔️ | ||
SPAQ | ✔️ | ✔️ | ||
Waterloo_Exploration | ✔️ | ✔️ | ||
✔️ (code only) | ✔️ |
-
Prerequisites
pip install wget
-
General Python (please refer
demo.py
)from load_dataset import load_dataset dataset = load_dataset("LIVE")
-
PyTorch (please refer
demo_pytorch.py
)from load_dataset import load_dataset_pytorch dataset = load_dataset_pytorch("LIVE")
-
General Python (please refer
demo.py
)from load_dataset import load_dataset dataset = load_dataset("LIVE", dataset_root="data", attributes=["dis_img_path", "dis_type", "ref_img_path", "score"], download=True)
-
PyTorch (please refer
demo_pytorch.py
)from load_dataset import load_dataset_pytorch transform = transforms.Compose([transforms.RandomCrop(size=64), transforms.ToTensor()]) dataset = load_dataset_pytorch("LIVE", dataset_root="data", attributes=["dis_img_path", "dis_type", "ref_img_path", "score"], download=True, transform=transform)