Image aesthetics: a twiddler for how good an image looks
Image aesthetics has signals per query and per result. RESONEO says it scores aesthetic quality; how, and with what weight, is unknown.
01What is known
The twiddler has two schema objects in the image_twiddler namespace: ImageAestheticsTwiddlerRanklabQuerySignals for the query and ImageAestheticsTwiddlerRanklabResultSignals for each result. "Ranklab" appears in the object names; no source available to us explains what that part of the name refers to.
RESONEO describes it as scoring how aesthetically pleasing an image is, both in relation to the search and per result. The query part would let it matter more for some searches, say wallpapers, than for others. Like every twiddler, it only recommends; the framework in Superroot, the layer that merges results from Google's indexes before the page is built, makes the call.
02What is not known
What model computes the score, how it relates to the EQ* and TQ* values named in the leak for the image boost twiddler, and how much it moves a result are all unknown. The overlap in topic is obvious, but no source connects the two.
On our map it belongs to the twiddler layer and to no E-E-A-T system. It is a rule for how image results are assembled, not a judgement on who made a page.