Is it really the same thing? The method you cite is a type of style transfer. Input sharp focused image and you get a blurrier version out with the required style. You’re removing information with a particular type of convolution.
The nvidia version seems to inpaint new details into the user segmented areas, like a collage of sorts.
"we first label a photograph or painting by hand to indicate its component textures. We then give a new labeling, from which the analogies algorithm produces a new photograph"
DL approach generalizes over many images and can derive some some "idea" of how given class should look like (ie. a tree)
Specifically this is the "texture-by-numbers" application. Ex: https://www.mrl.nyu.edu/projects/image-analogies/potomac.htm...
Every single fancypants application of neural nets in graphics today is a retread of one of the applications of the Image Analogies algorithm.