I added the ? when I could not read it. Normal SR can only do so much with a 3x3 pixel blur.
But their bottom line is mostly correct because their process also uses larger versions of the same pattern to replace the smaller ones.
So, there was not a much larger T, so it made a little fuzzball instead. So I wrote "?".
There are '?' characters in the paper's PDF as well, page 7.
>So where are the '?' coming from? I think I have to call shenanigans / database, there aren't any in the image, or even any shapes like it.
How about it's what they output when they are not sure?
>Fig. 6 [the eye chart] compares our unified SR result against ground truth. In Fig. 7 [baby with hat] we compare our method to results from [11,13] and [9]. Note that our results are comparable, even though we do not use any external database of low-res/highres pairs of patches [11, 13], nor a parametric learned edge model [9]. Other examples with more comparisons to other methods can be found in the paper’s website.