[samkater]

I’m not an expert, but my light reading of the paper makes it seem like it isn’t “random noise” in the colloquial sense, but more like “there are properties to the randomness even though the images look like noise.”

The abstract seems to say that, but again, I could be misinterpreting: “Our findings show that it is important for the noise to capture certain structural properties of real data but that good performance can be achieved even with processes that are far from realistic.”

[jswulff]

That is correct -- by "noise", we don't meet pixel noise, but instead a stochastic process (in fact, different processes different properties which we compare in the paper) from which we can sample large amounts of varied training images.

[Retric]

Except your not actually training on noise, your training on procedurally generated images which include random modifications. It’s just the summery is really bad at describing the process.