distillpub / post--differentiable-parameterizations

A powerful, under-explored tool for neural network visualizations and art.
https://distill.pub/2018/differentiable-parameterizations
Creative Commons Attribution 4.0 International
26 stars 12 forks source link

Revise the end of 3d style transfer section #66

Closed znah closed 6 years ago

znah commented 6 years ago

[ ] I propose dropping this:

The resulting textures combine elements models of the desired style, while preserving the characteristics of the original texture. Take as an example the model created by imposing Van Gogh's starry night as style image. The resulting texture contains the repetitive and vigorous brush strokes that characterize Van Gogh's work. However, despite the style image contains only cold tones, the resulting fur has a warm orange undertone as it is preserved from the original texture. Even more interesting is how the eyes of the bunny are preserved when different styles are transfered. For example, when the style is obtained from the Van Gogh's painting, the eyes are transformed in a star-like swirl, while if Kandinsky's work is used, they become abstract patterns that still resemble the original eyes.

because:

[ ] Need to say more about weighted gram matrices over iterations, and it's implementation with tf.stop_gradients

[ ] Footnote 13 should either link to shapeways material description, or be removed.

znah commented 6 years ago

We cite three papers on 3d printing, and none of them says anything about multicolor 3d printing