Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
1–10 of 68 posts
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#2Generated images start at 0:43 in the video. Link to paper here:
http://research.nvidia.com/sites/default/files/pubs/2017-10_...
Source: NVIDIA
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#3I’ve seen this going around twitter and the video looks cool but I don’t really understand what’s going on.
Can someone explain it in layman’s terms?
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#4I’ve seen this going around twitter and the video looks cool but I don’t really understand what’s going on. Can someone explain it in layman’s terms?
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#5A GAN is a Generative Adversarial Network[0], the video is like animated Deep Dream[1] stuff but way more refined.
I don't like the horizontal sliding transition because I'm way focused on the bizarre iterations of the various targets.
Gonna have to update our camouflage patterns again to combat computer vision...
[0]: https://en.m.wikipedia.org/wiki/Generative_adversarial_netwo...
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#6Interesting. In another 300-500 years, I am pretty sure we will start simulating sensory experience and ultimately the past. I am not sure if I am a toy simulation of the past from the future, right now.
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#7I’ve seen this going around twitter and the video looks cool but I don’t really understand what’s going on. Can someone explain it in layman’s terms?
Neural Networks are really good at identifying patterns in data. As a classic example, if you wanted to predict housing prices, you could build a data set that maps features about houses (square feet, location, proximity to Caltrain, etc) onto their actual price, and then train a network to recognize the complex relationship between features and pricing. Training happens by feeding the network features, letting it make a guess about the price, and then correcting the guess (backpropagation).
Convolutional Neural Networks work similarly, but with images. Instead of giving a CNN discrete features, you'll usually just use the pixels of the image itself. Through a series of layers, the CNN is able to build features itself (traditionally things like edges, corners) and learn patterns in image data. For example, a CNN might be trained on a dataset that maps images onto labels, and learn how to label new images on its own.
This video uses Generative Adversarial Networks (GANs) to actually generate new images. In this case, you have two networks "competing" against each other. One network is a traditional CNN trying to identify is an image is "real" or computer generated, and the second network tries to generate new images to trick the first network.
We've been able to generative fairly realistic small images before (usually 64x64), but doing it this well on high-resolution (1024x1024) images is unprecedented.
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#8Holy crap that video. It makes me think of the scramble suit from A Scanner Darkly[1]
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#9Well, I guess the propaganda bots will be a little more convincing now that they can have unique profile photos.
Would be nice if I could use this to convince Facebook that some fictional image is myself, though.
Re: Progressive Growing of GANs for Improved Quality, Stability, Variation [video]
#10Looking at synthetic celebrities is unsettling. They're all familiar. They're obviously celebrities, but it's impossible to remember their names.