Chroma key benchmark

We measured the keyer behind this site against two naive baselines on six synthetic fixtures. Every number below is regenerated by one command from a seeded generator, and the full write-up is archived with a DOI. We claim no accuracy advantage over a naive RGB threshold — and this page explains why.

Setup

Results — mean IoU over the six fixtures

MethodThresholdMean IoU
Naive RGB distance (baseline A)oracle0.995662
Cb/Cr distance keyer (this site)best tolerance0.994378
Cb/Cr distance keyer (this site)25 — shipped default0.873398
Green-dominance rule (baseline B)oracle0.657181

What the table actually says

A naive RGB threshold matches us to within 0.002 mean IoU. That is the honest reading, and it is why we do not advertise the keyer as more accurate. On flat, evenly lit, synthetic backdrops, any colour-distance rule saturates — there are only two kinds of pixel, and any threshold separates them. A benchmark like this has almost no discriminating power.

What does separate the methods is the case where the assumption breaks:

Limits you should hold us to

Full write-up

The preprint with the method, the fixture construction and the complete tables is archived at doi.org/10.5281/zenodo.22916767 (CC BY 4.0). The source and the CSVs are in the chroma-key-reference repository.

Open the tool