A Style-Based Generator Architecture for Generative Adversarial Networks
Why Hacker News recommends it
Cited as an example of how realistic GAN-generated faces had become, and of what a well-structured latent space can do.
What it is
A short demo video for NVIDIA's StyleGAN paper, which proposes a style-based generator for GANs. It shows face synthesis with style mixing and scale-specific control over attributes like pose and freckles.
Recommended by 0 HN commenters across 0 different months, 2018 to 2019.
What Hacker News said
Cites backpropaganda · 2018-12 · on “Artificial Intelligence Creates Realistic Pictures of People”
Note that isn't tabula rasa generation. All these faces are generated from reference images. See this timestamped video for example: [this video] . Current deep generative tech requires a carefully designed dataset of images with controlled variation. For the faces above, a dataset of celebrity faces was carefully constructed from a larger wild dataset, so as to not have any rare features, and the eyes and noses were aligned, making the dataset digestible by a GAN. This particular method then also uses multiple style images which it takes certain features from to mix up and create the mixture face. The main problem with this tech is that the quality can not be reliably controlled. Whatever it gen
Cites Liquix · 2019-04 · on “Name one thing in this photo”
Do you believe this kind of thing should be/is detectable if you're looking for it hard enough? This is pretty realistic: [this video]
Cites Veedrac · 2019-07 · on “Microsoft is investing $1B in OpenAI”
> What exactly is incredible (relatively) about the current state of things? Compared to 1999? Watch [this video] Hear [LINK] Read [LINK] These are not just ‘increasing numbers’. These are fucking witchcraft, and if we didn't live in a world with 5 inch blocks of magical silicon that talk to us and giant tubes of aluminium that fly in the sky the average person would still have the sense to recognize it. > It is the way to save this field from [...] For us to have a productive conversation here you need to either respond to my criticisms of this line of argument or accept that it's wrong. Being disingenuous because you like what the argument would encourage if it were true doesn't help when your
Cites Veedrac · 2019-08 · on “The body is the missing link for truly intelligent machines (2017)”
“Not all that difficult” is in the context of the brain, where things tend to vary between ‘pretty difficult’ and ‘seemingly impossible’. I say ML shows pattern matching of this sort isn't all that difficult because progress has been significant over very short stretches of time, without any particular need to solve hard problems, and with a general approach that looks like it will extend into the future. We have this famous image showing progress over the last 5 years. [LINK] The latest generator in this list has very powerful latent spaces, including approximately accurate 3D rotations. [this video] We have similarly impressive image segmentation and pose estimation results. [LINK] Because you