Leaderboard of the MSU Video Quality Metrics Benchmark

Leaderboard

The chart below shows the correlation of metrics with subjective scores on our dataset. You can choose the type of correlation and compression standard of codecs used for compression. We recommend that you focus on Spearman’s rank correlation coefficient.

Correlation type: Compression Standard:

The table below shows the correlations of metrics with subjective scores on our dataset. Click on the labels to sort the table.

Correlation type:

To analyze metric performance in more detail, we added a few mutually nonexclusive categories with 196 videos from the dataset: Shaking, Nature, Sports, Gaming / Animation.

Correlation type:

Metrics performance on different compression standards

Below you can see the comparison of the metrics performance on videos compressed by codecs with different compression standards. In addition, the chart shows 95% confidence interval for each point.

Correlation type:

Speed-Quality Plot

Chart below shows Speed-Quality characteristics of metrics.

Correlation type:

Submitting

To submit your method please visit this section of the home page.

Contacts

We would highly appreciate any suggestions and ideas on how to improve our benchmark. Please contact us via email: vqa@videoprocessing.ai.

Cite us

@inproceedings{
NEURIPS2022_59ac9f01,
author = {Antsiferova, Anastasia and Lavrushkin, Sergey and Smirnov, Maksim and Gushchin, Aleksandr and Vatolin, Dmitriy and Kulikov, Dmitriy},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
pages = {13814--13825},
publisher = {Curran Associates, Inc.},
title = {Video compression dataset and benchmark of learning-based video-quality metrics},
url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/59ac9f01ea2f701310f3d42037546e4a-Paper-Datasets_and_Benchmarks.pdf},
volume = {35},
year = {2022}
}

You can find the full text of our paper through the link.

12 Mar 2022
See Also
MSU CVQAD – Compressed VQA Dataset
During our work we have created the database for video quality assessment with subjective scores
Video Upscalers Benchmark
The most extensive comparison of video super-resolution (VSR) algorithms by subjective quality
Site structure