Explore subjective comparisons of the video distortion algorithms

Everyone is welcome to participate! Run your favorite Deblurring/Denoising/Super-Resolution/Compression method on our dataset and send us the result to see how well it performs. Check the “Submitting” section to learn the details.

What’s New

• March 2nd, 2026: Release

Introduction

Subjective QRS Benchmark provides large-scale human preference rankings for video restoration and compression algorithms. We start from a large pool of openly licensed video segments and select a diverse subset of 1,000 source clips via feature-based clustering.

Each source clip is then processed by multiple algorithm families:

• Deblurring
• Denoising
• Super-Resolution
• Compression

Algorithms results form the benchmark’s pool of distorted videos.

A large crowdsourcing study is conducted on these outputs using pairwise subjective comparisons, and the collected votes are aggregated into the task-specific rankings shown below. Alongside subjective scores.

Scroll below for comparison tables of model results.

Deblurring Leaderboard

Denoising Leaderboard

Super-Resolution Leaderboard

Compression Leaderboard

Submitting

To add your method to the benchmark, follow these steps:

1. Download the dataset

2. Apply your method to the dataset

3. Send to subjective-qrs-benchmark@videoprocessing.ai the following information: The full and short names of the method that we will specify in our benchmark. An compressed directory with the results of method inference. The link must be valid within a month after receiving it. Please ensure that you permit us to download the file. By submitting this video, you agree that third parties may use it. The exact commands, options, versions of used programs, etc. Each submission must contain results of exactly one model with fixed settings. Please do not fine-tune model parameters by hand for each video segment. If you want us to verify your method, send us the executable, and we will run it ourselves. Then we will mark the FPS of your algorithm as “Verified” in charts and tables. Executable's arguments must include paths to the folder with inpu videos and the folder for output videos. By submitting this executable, you agree that third parties may use it.

If you have any suggestions or questions, please contact us: subjective-qrs-benchmark-benchmark@videoprocessing.ai

Get Notifications About the Updates of This Benchmark

Do you want to be the first to discover the best new Deblurring/Denoising/Super-Resolution/Compression algorithm? We can notify you about this benchmark’s updates: simply submit your preferred email address using the form below. We promise not to send you unrelated information.

Further Reading

Check the “Methodology” section to learn how we prepare our dataset.

Check the “Participants” section to learn which method implementations we use.