News for hackers. Stuff that matters.
Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by ebg13 on Thursday April 11, 2019 @05:45PM (#19639570)
If you want to see the same thing done 18 years ago without new-age machine learning, read https://www.mrl.nyu.edu/projects/image-analogies/index.html IMO the most elegant vision/graphics algorithm ever written.

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.

Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by knolan on Thursday April 11, 2019 @06:05PM (#19639739)
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.

Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by llukas on Thursday April 11, 2019 @06:01PM (#19639712)
This is not same:

"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)

Re:Photos from Crude Sketches: Nvidia's GauGAN Explained Vis... by pmayrgundter on Friday April 12, 2019 @03:26AM (#19642762)
Wow, thanks for sharing!