This is probably less a critique of your project and maybe more a celebration of cubism: The clock in the Picasso portrait is not "harmonized" in terms of cubist motifs at play in the composition. The contours appear merely dilapidated. Maybe this passes for someone with little concern for painting or art history but it was like a sort thumb for me. Maybe this is a good study reference on the gap between pattern recognition and human perception. Maybe not. I'd be interested in other thoughts.
What's more impressive is that several of them work quite well, and barring anachronism, at the sizes given in the samples you might not know what was added if they didn't point it out. The park bench I found particularly impressive, for instance. I suspect if we increased the resolution it would break down, but at this size it works pretty well.
In general, it’s definitely impressive how well they work.
It would be interesting to see them do a higher resolution version, or if they have them. It's possible it would indeed fit right in even so; now that I think about it the microscale of these paintings are probably very stereotypical and the algorithm might be able to reproduce them well. It would be especially interesting to see if it would correctly reproduce brush strokes, which have a lot of context to them. Given that "deep learning" can do things like reproduce the structure of a TV script accurately, it doesn't seem out of the question.
Getting the colors right is half the problem, and I guess the histogram loss function I saw mentioned at the bottom of the page does that. A couple of the results had strange looking color transformations though - the little girl whose red shirt turns blue, even though the bed has some red in it, and the red rose that turns yellow even though there are orange flowers in the background. So it's not always choosing colors that are the closest to the source while being available in the target's palette. Anyone know why the colors sometimes go so far of course?
Also, this is one of the first style transfer papers I've seen that has a pretty obvious built-in and seemingly plausible business idea. I'm sure poster stores in malls everywhere could sell versions of your favorite painting or poster with your or your own face or something else of your choice added to the composition. It's like the new version of the picture board painting with face cutouts, but way better.
Is there something about what this file does that is easier accomplished in Matlab or is it just two different people preferring different languages?
For example, often the color of the inserted object changes radically, which might not be what was intended.
I'd love to see more things like this with Rothko, Pollock, etc.