This content was created by LARRUZ. This content was uploaded by LARRUZ. This is a YouTube video titled "High-Resolution Neural Texture Synthesis | Two Minute Papers #221" (uploaded 2018-01-17T17:23:51+00:00). The excerpt is an English narrated transcript featuring two speakers (hosts/narrators) from the Two Minute Papers series. They explain deep convolutional neural networks and a new multi-scale neural texture synthesis method that produces high-frequency, visually crisp textures, discuss its limitations (it mimics statistical properties but not semantic meaning), note the source code is available under the MIT license, and include a Patreon/support call-to-action. The context is a short research-summary video describing the method and demonstrating results.
Questions this video answers
Permissive MIT license.
Chapters
Dear fellow scholars, this is two minute papers with deep learning means that we are working with neural networks that contain many inner layers, as neurons in each.
Layer combine information from the layer before.
The deeper we go in these networks, the more elaborate details we're going to see. Let's have a look at an example. For instance, if we train a neural network to recognize images of human faces, first we'll see an edge detector, and as a combination of edges, object parts will emerge in the next layer.
And in the later layers, a combination.
Of object parts create object models.
Neural texture synthesis is about creating lots.
Of new images based on an input texture. And these new images have to resemble, but not copy the input.
Previous works on neural texture synthesis focused on how different features in a given.
Layer relate to the ones before and after it.
The issue is that because neurons in.
Convolutional neural networks are endowed with a small receptive field, they can only look at an input texture at one scale. So, for instance, if you look here, you see that with previous techniques, trying to create small scale details in a synthesized texture is going to lead to rather poor results. This new method is about changing the inputs and the outputs of the network to be able to process these images at different scales. These scales range from coarser to finer versions of the same images. Sounds simple enough, right? This simple idea makes all the difference. Here you can see the input texture and here's the output. As you can see, it has different patterns, but has very similar properties to the input.
And if we zoom into both of.
These images, we can see that this.
One is able to create beautiful high.
Frequency details as well.
Wow, this is some really, really crisp output.
Now, it has to be emphasized that this means that the statistical properties of the original image are being mimicked really well. What it doesn't mean is that it takes into consideration the meaning of these images.
Just have a look at the synthesized.
Bubbles or the flowers here. The statistical properties of the synthesized textures may be correct, but the semantic meaning of the input is not captured. Well, in a future work, it would.
Be super useful to extend this algorithm.
To have a greater understanding of the structure and the symmetries of the input images into consideration.
The source code is available under the.
Permissive MIT license, so don't hold back those crazy experiments.
If you have enjoyed this episode and.
You think the series provides you value or entertainment, please consider Supporting us on Patreon 1. Time payments and cryptocurrencies like Bitcoin or Ethereum are also supported and have been massively successful. I am really out of words. Thank you so much. The details are available in the video description.
Thanks for watching and for your generous support. Now, see you next time.
