readme.md

November 7, 2024 ยท View on GitHub

A Unified Interface for IQA Datasets

This repository contains a unified interface for downloading and loading 31 popular Image Quality Assessment (IQA) datasets. We provide codes for both general Python and PyTorch.

Citation

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}
        }

Supported Datasets

DatasetDis ImgRef ImgMOSDMOS
LIVE:heavy_check_mark::heavy_check_mark::heavy_check_mark:
A57:heavy_check_mark::heavy_check_mark::heavy_check_mark:
LIVE_MD:heavy_check_mark::heavy_check_mark::heavy_check_mark:
MDID2013:heavy_check_mark::heavy_check_mark::heavy_check_mark:
CSIQ:heavy_check_mark::heavy_check_mark::heavy_check_mark:
KADID-10k:heavy_check_mark::heavy_check_mark::heavy_check_mark:(Note)
TID2008:heavy_check_mark::heavy_check_mark::heavy_check_mark:
TID2013:heavy_check_mark::heavy_check_mark::heavy_check_mark:
CIDIQ_MOS100:heavy_check_mark::heavy_check_mark::heavy_check_mark:
CIDIQ_MOS50:heavy_check_mark::heavy_check_mark::heavy_check_mark:
MDID2016:heavy_check_mark::heavy_check_mark::heavy_check_mark:
SDIVL:heavy_check_mark::heavy_check_mark::heavy_check_mark:
MDIVL:heavy_check_mark::heavy_check_mark::heavy_check_mark:
Toyama:heavy_check_mark::heavy_check_mark::heavy_check_mark:
PDAP-HDDS:heavy_check_mark::heavy_check_mark::heavy_check_mark:
VCLFER:heavy_check_mark::heavy_check_mark::heavy_check_mark:
PIPAL:heavy_check_mark::heavy_check_mark::heavy_check_mark:
LIVE_Challenge:heavy_check_mark::heavy_check_mark:
CID2013:heavy_check_mark::heavy_check_mark:
KonIQ-10k:heavy_check_mark::heavy_check_mark:
SPAQ:heavy_check_mark::heavy_check_mark:
AADB:heavy_check_mark::heavy_check_mark:
BIQ2021:heavy_check_mark::heavy_check_mark:
FLIVE:heavy_check_mark::heavy_check_mark:
GFIQA:heavy_check_mark::heavy_check_mark:
AVA:heavy_check_mark::heavy_check_mark:
PIQ2023:heavy_check_mark::heavy_check_mark:
UHD-IQA:heavy_check_mark::heavy_check_mark:
Waterloo_Exploration:heavy_check_mark::heavy_check_mark:
BAPPS:heavy_check_mark::heavy_check_mark:2AFC (no JND)
PieAPP:heavy_check_mark::heavy_check_mark:2AFC
KADIS-700k:heavy_check_mark: (code only):heavy_check_mark:

Installation

You can install this package in two ways:

  1. Install from PyPI (recommended)

    pip install iqadataset

  2. Build from source (most updated)

    git clone https://github.com/icbcbicc/IQA-Dataset.git
cd IQA-Dataset
pip install -e .

Basic Usage

  1. General Python (please refer demo.py)

    from iqadataset import load_dataset
dataset = load_dataset("LIVE")

  2. PyTorch (please refer demo_pytorch.py)

    from iqadataset import load_dataset_pytorch
dataset = load_dataset_pytorch("LIVE")

Advanced Usage

  1. General Python (please refer demo.py)

    from iqadataset import load_dataset
dataset = load_dataset("LIVE", dataset_root="data", attributes=["dis_img_path", "dis_type", "ref_img_path", "score"], download=True)

  2. PyTorch (please refer demo_pytorch.py)

    from iqadataset 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)

TODO

Star History

Star History Chart