A full-reference metric compares the impaired video against the complete pristine original, frame for frame and pixel for pixel, the way a proofreader checks a copy against the source document with both pages side by side. PSNR, SSIM, MS-SSIM, and VMAF are all full-reference, which is why they are the most accurate family and generally correlate best with human ratings, and why they own the lab: encoder comparison, regression suites, CI/CD quality gates, and video-on-demand QC. The catch is twofold. First, you must possess the master, so full-reference is useless on a live stream or user-generated clip that has no original. Second, the two videos must be aligned in time, space, and brightness; a small temporal, spatial, or luminance offset makes the metric report a quality collapse the eye would never see, so an unaligned score is broken, not low. Full-reference is the richest of the three reference setups, with reduced-reference and no-reference giving up information for reach.
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
A full-reference metric needs the pristine source, which makes PSNR, SSIM and VMAF fit for encoding labs but hard to use on live or user streams. We wrote seven volumes covering the whole video stack, and for full-reference metrics start with Volume 1: PSNR, SSIM and VMAF, alignment and scaling, and rate-quality comparisons. Written by Nikolay Sapunov, CEO at Fora Soft.
Deciding where a full-reference metric fits and where you need a no-reference one?
Tell us your pipeline: we map where full-reference metrics can run, where no-reference ones are needed and give you a measurement plan. 250+ video products shipped since 2005.
