VMAF
An Emmy-winning perceptual video quality assessment algorithm that fuses multiple metrics to predict human visual quality.
What is VMAF?
VMAF is an open-source perceptual video quality assessment algorithm developed by Netflix that predicts human visual quality by fusing multiple elementary metrics. It solves the problem of accurately measuring video quality as perceived by viewers, which is critical for optimizing video encoding, streaming, and quality assurance workflows. The project includes a C library, Python tools, and integrations with FFmpeg and Docker.
Video engineers, researchers, and developers working on video encoding, streaming optimization, quality assessment, and media processing pipelines who need accurate perceptual quality metrics.
Developers choose VMAF because it provides a more human-aligned quality metric than traditional tools like PSNR or SSIM, is backed by Netflix's extensive research, and offers high performance through optimized implementations and flexible integration options.
Overview
Perceptual video quality assessment based on multi-method fusion.
Use Cases
Best For
- Optimizing video encoding settings for streaming services
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.