Doesn't it?

You arbitrarily picked 16 possible photorealistic faces out of a total solution space of what? Millions?

Wouldn't the balance of probability be on someone in the general population of humans more closely resembling one of your 16 candidate images than any of your candidates resembling the Ground Truth image?

Doesn't the problem get both better and worse as you scale your N up from 16? That is, it would be better because one of your candidates is more likely to match the Ground Truth, but it would be worse because you've also widened your net for catching false positives?