New arxiv.org paper that looks extremely similar to this project

[ProGamerGov]

So I just found this research paper here: https://arxiv.org/ftp/arxiv/papers/1612/1612.00085.pdf, that's titled "Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution". It seems to detail the same process/technique as this project.

It was submitted to arxiv.org on Dec 1st: https://arxiv.org/abs/1612.00085

[0000sir]

Someone come out with the same idea :) You're reading so many papers, I hope I can do it too They did a lot of complex works I totally can't understand, I'm not expert of computer graphics, only a coder have a job to feed my family ;-( Thank you for the information, I'm glad someone have the same idea or inspired by this idea, that's why we opened the source codes :)

[ProGamerGov]

I definitely think the tiling method is superior to Neural-Enhance, and it's awesome to see research into this area that can be used to improve our neural artwork.

There is also this research paper here that uses a complimentary method of dynamic scaling factor for patch-matching instead of a global scaling factor like the "Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution" details.

Source

[0000sir]

The links you posted is very interesting, I never imaged neural network can be used to do this. just like CSI.. dude, that's amazing!!!

BTW, I tried this project texture_nets to accelerate style transfers. May be you already known about it, but it helps me a lot.