libvmaf

{
  "aliases": [],
  "alternatives": [
    "PSNR",
    "SSIM",
    "FFmpeg libavfilter",
    "x264",
    "x265"
  ],
  "build_dependencies": [
    "meson",
    "ninja"
  ],
  "categories": [
    "library",
    "video-tool",
    "benchmark"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Perceptual video quality assessment based on multi-method fusion",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:38+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "libvmaf",
  "github_default_branch": "master",
  "github_last_commit_at": "2026-06-20T01:19:09Z",
  "github_readme_excerpt": "# VMAF - Video Multi-Method Assessment Fusion\n\n[![libvmaf](https://github.com/Netflix/vmaf/actions/workflows/libvmaf.yml/badge.svg)](https://github.com/Netflix/vmaf/actions/workflows/libvmaf.yml)\n[![Windows](https://github.com/Netflix/vmaf/actions/workflows/windows.yml/badge.svg)](https://github.com/Netflix/vmaf/actions/workflows/windows.yml)\n[![ffmpeg](https://github.com/Netflix/vmaf/actions/workflows/ffmpeg.yml/badge.svg)](https://github.com/Netflix/vmaf/actions/workflows/ffmpeg.yml)\n[![Docker](https://github.com/Netflix/vmaf/actions/workflows/docker.yml/badge.svg)](https://github.com/Netflix/vmaf/actions/workflows/docker.yml)\n\nVMAF is an [Emmy-winning](https://theemmys.tv/) perceptual video quality assessment algorithm developed by Netflix. This software package includes a stand-alone C library `libvmaf` and its wrapping Python library. The Python library also provides a set of tools that allows a user to train and test a custom VMAF model.\n\nRead [this](https://medium.com/netflix-techblog/toward-a-practical-perceptual-video-quality-metric-653f208b9652) tech blog post for an overview, [this](https://medium.com/netflix-techblog/vmaf-the-journey-continues-44b51ee9ed12) post for the tips of best practices, and [this](https://netflixtechblog.com/toward-a-better-quality-metric-for-the-video-community-7ed94e752a30) post for our latest efforts on speed optimization, new API design and the introduction of a codec evaluation-friendly [NEG mode](resource/doc/models_v0.md#disabling-enhancement-gain-neg-mode).\n\nAlso included in `libvmaf` are implementations of several other metrics: PSNR, PSNR-HVS, SSIM, MS-SSIM and CIEDE2000.\n\n![vmaf logo](resource/images/vmaf_logo.jpg)\n\n## News\n\n- (2026-06) We are releasing a new set of VMAF models (**v1**). See [tech blog](https://medium.com/netflix-techblog/vmaf-v1-good-is-not-good-enough-60d7e4244ea8) for more information on v1. See [models_v1.md](resource/doc/models_v1.md) for details and model selection guidance. The previous generatio",
  "github_repo": "Netflix/vmaf",
  "github_stars": 5377,
  "github_topics": [],
  "homepage": "https://github.com/Netflix/vmaf",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 82545,
  "installs_365d": 728434,
  "installs_90d": 297974,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "BSD-2-Clause-Patent",
  "llm_generated_at": "2026-06-20T23:42:23+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "libvmaf",
  "oldnames": [],
  "one_liner": "C library for perceptual video quality assessment using Netflix\u0027s Emmy-winning VMAF algorithm.",
  "optional_dependencies": [],
  "rank_30d": 54,
  "rank_365d": 90,
  "rank_90d": 48,
  "raw_hash": "c92ed646720f67de",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/lib/libvmaf.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [
    {
      "vim": "build"
    }
  ],
  "version_head": null,
  "version_stable": "3.2.0",
  "versioned_formulae": [],
  "why_use_this": "Essential for video encoding workflows that need objective quality metrics beyond PSNR/SSIM. Integrates with FFmpeg and provides both C library and Python bindings, making it suitable for batch transcoding pipelines, codec comparisons, and automated quality monitoring. Widely adopted in streaming services for ground-truth quality evaluation."
}