Explore the best video colorization algorithms!

Our benchmark evaluates the best video colorization methods for color propagation and automatic colorization.

Everyone is welcome to participate! Apply your video colorization method to our dataset and submit the results to see how well it performs. Check the Submitting section to learn the details.

What’s New

• July, 2024: Benchmark Release

Introduction

For a comprehensive assessment of the video colorization task, we used various objective metrics and subjective comparison. Over 2000 valid participants have selected the most visually appealing colorization result in a number of pairwise comparisons. In addition, we calculated the FPS (frames per second) to compare the speed of both algorithms and metrics.

Check the Methodology section to learn the details.

Scroll below for comparison charts, tables, and interactive visual comparisons of video colorization models result.

Leaderboards

Charts

Visualizations

Submitting

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

1. Download the dataset

2. Apply your video colorization method to the dataset

3. Send to video-colorization-benchmark@videoprocessing.ai the following information: The full and short names of the video colorization method that we will specify in our benchmark. Also provide information about how many anchor frames were used. An compressed directory with colorized frames or videos. 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 add the FPS of your algorithm in charts and tables. Executable's arguments must include paths to the folder with input PNG images and the folder for output PNG images. By submitting this executable, you agree that third parties may use it.

You can verify the results of current participants or estimate the perfomance of your method on public samples of our dataset!
Download ground truth for public samples using dataset link above, to see metrics on the sample, choose "Open" option in "Data" switch.

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

Get Notifications About the Updates of This Benchmark

Do you want to be the first to discover the best new video colorization 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 “Metrics” section to learn more about metrics and their correlations.

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