Netflix vmaf: Perceptual video quality assessment based on multi-method fusion
tosh
22 points
8 comments
October 18, 2026
Related Discussions
Found 5 related stories in 101.7ms across 9,867 title embeddings via pgvector HNSW
- Getting video models to learn better, faster schopra909 · 16 pts · August 27, 2026 · 51% similar
- Flux 3: One multi-modal model for Image, Video, Audio and Action-Prediction meetpateltech · 11 pts · July 23, 2026 · 50% similar
- Laion Big Video Dataset ks2048 · 37 pts · August 27, 2026 · 50% similar
- SANA-Video 2.0 ilreb · 11 pts · July 24, 2026 · 48% similar
- Project HydraFusion: Frontier quality via multi-model orchestration qainsights · 64 pts · September 04, 2026 · 46% similar
Discussion Highlights (3 comments)
fishgoesblub
I was hoping this would be a post announcing the death of VMAF from Netflix, alas.
djoldman
Blog post about the latest version: https://netflixtechblog.com/vmaf-v1-good-is-not-good-enough-...
anematode
VMAF is super cool, although not the end-all-be-all of video quality measurement for sure. I'm currently evaluating switching over to the new v1.0 models. The (unsolicited) slop PRs on that repository are a sight to behold, though. The same slopper posted an aggressive response to my PR: https://github.com/Netflix/vmaf/pull/1586