Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

Correct code link:

https://github.com/chuanli11/MGANs

Collection of other implementations of this feedforward neural style transfer approach:

https://tensortalk.com/?cat=feedforward-neural-style-transfe...

Or, regular neural style transfer:

https://tensortalk.com/?cat=neural-style-transfer

They also have a video with some samples and an overview.

https://www.youtube.com/watch?v=PRD8LpPvdHI

code here https://github.com/chuanli11/CNNMRF

Since it seems this paper's primary focus is on performance, it'd be interesting to see how this technique stacks up against one of those fancy new binary networks (e.g. http://arxiv.org/abs/1603.05279)

What is texture synthesis usually used for?

Publishing papers.

Games. Good texture synthesis can augment or replace the texture creation process in games which often rely on hand-painting and manual seam-removal in Photoshop[0][1].

[0] https://www.allegorithmic.com/products/substance-painter [1] http://quixel.se/