An IQA toolbox with pure python and pytorch. Please refer to Awesome-Image-Quality-Assessment for a comprehensive survey of IQA methods, as well as download links for IQA datasets.

This is a image quality assessment toolbox with pure python and pytorch. We provide the following features:

• ✨ Comprehensive. Support many mainstream full reference (FR) and no reference (NR) metrics
• ✨ Accurate. Results calibration of our implementation with official matlab scripts (if exist).
• ✨ Flexible. Support training new DNN models with several public IQA datasets
• ✨ Differentiable. Most methods support pytorch backward
• ✨ Convenient. Quick inference and benchmark script

Below are details of supported methods and datasets in this project.

• Feb 2, 2022. Add MUSIQ inference code, and the converted official weights. See Official codes.
• More

• ⬜ Benchmark with retrained models of DBCNN, NIMA, etc.
• ⬜ Add pretrained models on different datasets.

• Ubuntu >= 18.04
• Python >= 3.8
• Pytorch >= 1.8.1
• CUDA 10.1 (if use GPU)
• Other required packages in requirements.txt

# Install with pip
pip install pyiqa

# Install latest github version
pip install git+https://github.com/chaofengc/IQA-PyTorch.git

# Install with git clone 
git clone https://github.com/chaofengc/IQA-PyTorch.git
cd IQA-PyTorch
pip install -r requirements.txt
python setup.py develop 

Example test script with input directory and reference directory. Single image is also supported for -i and -r options.

# example for FR metric with dirs 
python inference_iqa.py -n LPIPS[or lpips] -i ./ResultsCalibra/dist_dir -r ./ResultsCalibra/ref_dir 

# example for NR metric with single image
python inference_iqa.py -n brisque -i ./ResultsCalibra/dist_dir/I03.bmp 

import pyiqa 

# list all available metrics
print(pyiqa.list_models())

# create metric with default setting
iqa_metric = pyiqa.create_metric('lpips').to(device)

# create metric with custom setting
iqa_metric = pyiqa.create_metric('psnr', test_y_channel=True).to(device)

# example for iqa score inference
# img_tensor_x/y: (N, 3, H, W), RGB, 0 ~ 1
score_fr = iqa_metric(img_tensor_x, img_tensor_y)
score_nr = iqa_metric(img_tensor_x)

Metrics which support backward can be used for optimization, such as image enhancement.

• You only need to unzip downloaded datasets from official website without any extra operation. And then make soft links of these dataset folder under datasets/ folder. Download links are provided in Awesome-Image-Quality-Assessment.
• We provide common interface to load these datasets with the prepared meta information files and train/val/test split files, which can be downloaded from download_link and extract them to datasets/ folder.

You may also use the following commands:

mkdir datasets && cd datasets 

# make soft links of your dataset
ln -sf your/dataset/path datasetname

# download meta info files and train split files
wget https://github.com/chaofengc/IQA-PyTorch/releases/download/v0.1-weights/data_info_files.tgz
tar -xvf data_info_files.tgz 

Examples to specific dataset options can be found in ./options/default_dataset_opt.yml. Details of the dataloader inferface and meta information files can be found in Dataset Preparation

Example to train DBCNN on LIVEChallenge dataset

# train for single experiment
python pyiqa/train.py -opt options/train/train_DBCNN.yml 

# train N splits for small datasets
python pyiqa/train_nsplits.py -opt options/train/train_DBCNN.yml 

Please refer to the results calibration to verify the correctness of the python implementations compared with official scripts in matlab or python.

Here is an example script to get performance benchmark on different datasets:

# NOTE: this script will test ALL specified metrics on ALL specified datasets
# Test default metrics on default datasets
python benchmark_results.py -m psnr ssim -d csiq tid2013 tid2008 

# Test with your own options
python benchmark_results.py -m psnr --data_opt options/example_benchmark_data_opts.yml

python benchmark_results.py --metric_opt options/example_benchmark_metric_opts.yml tid2013 tid2008

python benchmark_results.py --metric_opt options/example_benchmark_metric_opts.yml --data_opt options/example_benchmark_data_opts.yml

Please refer to benchmark results for benchmark results of traditional metrics.

Any contributions to this repository are greatly appreciated. Please follow the contribution instructions for contribution guidance.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The code architecture is borrowed from BasicSR. Several implementations are taken from

• IQA-optimization
• Image-Quality-Assessment-Toolbox
• piq
• piqa

We also thanks the following public repositories:

• MUSIQ
• DBCNN
• NIMA
• HyperIQA
• CNNIQA
• WaDIQaM

If you have any questions, please email [email protected]