Viewing profile — nuclai

Yes, it sounds possible with this code — but would require training a new network. Do you have a link to some examples?

(Author here.) Maybe it's worth moving to a GitHub issue. Try `--model=small`. The demo server limits the number of pixels to around 320x200 or 256x256 and can do only 4 at the sam…

(Author here.) Unlike most other non generative adversarial network (GAN) approaches to super-resolution, it does try to inject high-frequency detail; see the faces example on GitH…

(Author here.) If you have the luxury to train on domain-specific textures, the results will definitely be better. That's why I included all the training code in the repository as …

(Author here.) Did you see the faces example on the GitHub page? It was a domain-specific network trained adversarially for that purpose, but I have yet to see any super-resolution…

(Author here.) Yeah, I knew this would come up but decided to proceed with the pixelated comparison anyway. I couldn't get the GIFs to reflect the results because of 8-bit quantiza…

(Author here.) Absolutely! Using multiple super-resolution networks, not only continuity would present problems, but also blending between different regions. I agree there's a lot …

(Author here.) My biggest insight from this project is that super-resolution with neural networks benefits significantly from being domain specific. If you train on broader dataset…

Almost nobody in deep learning uses OpenCL. All the DL frameworks primarily focus on CUDA and that's where you get the best performance. OpenCL is off the beaten path and you pay f…

You can use any image as source, but to create annotations you have to do that yourself currently. Using simple segmentation libraries (or clustering) can do a good job for certain…

Oh, absolutely. It's an idea whose time had come ;-)

From that perspective, this research is two steps further than Neural Style, I wrote about it yesterday here: http://nucl.ai/blog/neural-doodles/ First, the paper I call "Neural Pa…

The semantic map remains static during the optimization, so it can be provided as a pre-computation (e.g. pixel labeling, semantic segmentation, etc.) or done by hand. The ones in …

The algorithm does the same thing every time (it's triggered on request), only the input is changed by the human modifying the doodle—as shown in the video. The output gets better …

Exactly, the doodling is done by humans and the machine paints the HD images based on Renoir's original. I've edited the blog post to clarify.

The research is based on work I did writing and improving @DeepForger ( http://twitter.com/deepforger ), an online service for "basic" style transfer. The GitHub is a standalone ve…

> This code does a little of that. Actually, the code does none of that ;-) All of the semantics are provided by the users: either as manual annotations or by plugging in an existi…

Thanks for clarifying, I'll update the README. The research paper does a better job of explaining this with its figures! The algorithm can only reuse combinations of patterns that …

You can specify two pairs of images (content+annotation) and it'll transfer the style from one to another as consistently as possible. The down side is that you need to find an alg…

No, do you have any good ones? As long as entire sections are colored (not just lines), and those colors match with the annotations of another image, it should work fine!

Both images have their patterns extracted by the NN, and the optimization then tries to match the best patches from one image with the other, performing gradient descent to adjust …

It's a pre-trained network on image classification dataset from 2014 called ImageNet. The network is called VGG, paper is here: http://arxiv.org/abs/1409.1556 There's no additional…

(Author here.) For details, the research paper is linked on the GitHub page: http://arxiv.org/abs/1603.01768 For a video and higher-level overview see my article from yesterday: ht…