Metric-Selection Decision Tool

A dependency-free Python script (standard library only) that asks a few guided questions — do you have the pristine original, what is the job, what content, what viewing device — and prints the metric or panel to use plus the exact FFmpeg/libvmaf command to compute it. Runs interactively or fully from flags for CI use; includes a --demo. This is cross-cutting asset B2, the companion to article 2.11. (ZIP containing 1 file(s) — scripts, datasets, provenance).

Download free PDF
Book cover: AI for Video, Volume 6 of the Fora Soft Video Engineering HandbookBook cover: Video Encoding, Volume 1 of the Fora Soft Video Engineering HandbookBook cover: Video Streaming, Volume 3 of the Fora Soft Video Engineering Handbook

The handbook · 7 volumes

Fora Soft Video Engineering Handbook

This metric-selection decision tool asks whether you have the original, what the job is, the content and the viewing device, then prints the metric to use with the exact FFmpeg and libvmaf command. We wrote seven volumes covering the video stack; start with Volume 1 on quality metrics, codecs and color, then Volume 3 on QoE monitoring and Volume 6 on AI models. Written by Nikolay Sapunov, CEO at Fora Soft.

Browse the handbook on Amazon →7 volumes · 9,000+ pages · Kindle & paperback

Choosing which quality metric to put into your encoding CI?

Tell us your content and target devices, and we will recommend a metric set, thresholds and the pipeline step where each check should run. 250+ video products shipped since 2005.

Book a 30-min call →WhatsApp →Email us →