Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

github.com

Post reply on HN
Print view View original

41–50 of 63 posts

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#41

Post by dahart »

boulos wrote: post #37
geofft wrote: post #27

Earlier quoted context omitted.

I agree with you, but I don't think anyone from Nvidia called it "open source" (I agree that 'dahart incorrectly did so). It's a shame that GitHub allows non-open-source code, but it does, and nothing else about it implies that it's open-source.

Fwiw, Dave (dahart) currently works for NVIDIA :).

Hang on, that’s purely incidental in this context. I don’t represent this project in any way, and I only called it open source on accident here. Nobody associated with the project has suggested that it’s open source by OSI’s standards.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#42

Post by twofornone »

mkl wrote: post #34

This produces a kind of artefact I haven't seen before, involving little chains of circles and diamonds, e.g. https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... , https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... (hair). I think they follow those glowing coordinate-ish lines from the internal representation. It also seems to have given some faces contact lenses! https://nvlabs-fi-cdn.nvidia…

I suspect because there's a lot of entropy in hair and because of the shape of the optimization function, (which might even have a spatial term) a regular pattern in such a noisy and hard to learn region falls into a local minimum while the rest of the image converges to the true minimum. There's a little meat left to optimize here, but you need to do it cleverly because there's no reason for a neural network to learn all the many combinations of hair pixels in this application. That could require as many parameters all the neurons involved in generating the faces, I'd bet.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#43

Post by RNCTX »

Scaevolus wrote: post #40
RNCTX wrote: post #39

> This material is based upon work supported by the US Defense Advanced Research Projects Agency (DARPA) under Contracts No.R00112030005, HR001120C0123, HR001120C0124 and FA8750-20-2-1004 and the Air Force Research Laboratory (AFRL) under Contract No. FA8750-20-2-1004. This is why AI is just a marketing term with no real future. There isn't room for corporations to profit from it out of the gate + into the future ind…

Nvidia makes most of their money selling GPUs as computational accelerators-- both generic CUDA and neural network applications. They don't _need_ to profit off their ML models. It's a value added service. Ensuring their hardware has marketshare at the leading edge of the ecosystem is the main point.

They didn't profit off of ML models, they profited from the DARPA contract. See point above about murder robots.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#44

Post by captainmuon »

mkl wrote: post #34

This produces a kind of artefact I haven't seen before, involving little chains of circles and diamonds, e.g. https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... , https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... (hair). I think they follow those glowing coordinate-ish lines from the internal representation. It also seems to have given some faces contact lenses! https://nvlabs-fi-cdn.nvidia…

Looks like lizard people...

I wonder if you can't just put a bunch of results with and without artifacts into two different bins, and do another round of training on them. But I don't know enough about how style transfer and retraining of these nets and all that modern stuff works to tell if that is feasible.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#45

Post by dahart »

kube-system wrote: post #32
metagame wrote: post #19

Earlier quoted context omitted.

The Open Source Initiative coined the term to begin with. Using it incorrectly is harmful, and is how we've ended up with "literally" meaning "figuratively" in modern English. By insisting on the correct definition, I'm trying to prevent the same from happening to open source. It's pretty offensive to act like it's not a big deal to use something so essential to computing freedom in a cavalier way to intentionally le…

OSI was not the first to use the phrase "open source". This phraseology was in commonplace use to refer to other types of publicly available material for decades prior to 1998, when OSI decided to use the term to describe software licenses. One example from 1971: https://www.google.com/books/edition/United_States_Code/3j2P... There are also other (quite valid) authorities on software licensing other than OSI which ha…

Another problem with assuming that a non-commerce clause in the license automatically means software is not open source is that the US government defines commercial software as any software that is licensed to the public, which includes most open source software, even by OSI’s standards.

“in nearly all cases, open source software is considered "commercial software" by U.S. law, the FAR, and the DFARS. DFARS 252.227-7014 specifically defines "commercial computer software" in a way that includes nearly all OSS”

https://dodcio.defense.gov/open-source-software-faq/#Q:_Is_o...

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#46

Post by captainmuon »

avivo wrote: post #24

I appreciate the section on "Synthetic image detection": "While new generator approaches enable new media synthesis capabilities, they may also present a new challenge for AI forensics algorithms for detection and attribution of synthetic media. In collaboration with digital forensic researchers participating in DARPA's SemaFor program, we curated a synthetic image dataset that allowed the researchers to test and val…

> It's important to see this sort of thing happening more and more.

Why? If we insist on the authenticity of images, this is holding on to the old status quo in the same way we apply book and record copyright to digital content. We don't allow what the tech enables to the fullest, but we restrict it by pressing it into the old mold (e.g. by using DRM to make music a commodity).

I think "photographic proof" is a historical accident of the 20st century (and it was never perfect, those with resources could always manipulate pictures to some extent).

As a thought experiment, it might be interesting to imagine what happens when you "open up the dams" and are able to synthesize any image you can imagine! In the beginning, this will cause a lot of trouble (say with harrasment and fake news), but I believe society will adapt quickly. I think right now there is a real problem with the internet remembering too much (pervasive surveillance on the one hand, and constant risk of moral outrages for stupid things you did in your past). It would be an antidote if nobody could believe in any picture anymore.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#47

Post by twofornone »

twofornone wrote: post #42
mkl wrote: post #34

This produces a kind of artefact I haven't seen before, involving little chains of circles and diamonds, e.g. https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... , https://nvlabs-fi-cdn.nvidia.com/stylegan3/images/stylegan3-... (hair). I think they follow those glowing coordinate-ish lines from the internal representation. It also seems to have given some faces contact lenses! https://nvlabs-fi-cdn.nvidia…

I suspect because there's a lot of entropy in hair and because of the shape of the optimization function, (which might even have a spatial term) a regular pattern in such a noisy and hard to learn region falls into a local minimum while the rest of the image converges to the true minimum. There's a little meat left to optimize here, but you need to do it cleverly because there's no reason for a neural network to lear…

Thinking more about it, the shape of the solution space is sufficiently different for hair vs faces that any given combination of {optimization function, hyperparameters, training data} is unlikely to optimize for both. You probably need some other sort of special tuning, like a spatially local adaptive gradient for regions of hair.

Re: Nvidia releases Alias-Free GAN code and pre-trained models, naming it StyleGAN3

#48

Post by xg15 »

captainmuon wrote: post #46
avivo wrote: post #24

I appreciate the section on "Synthetic image detection": "While new generator approaches enable new media synthesis capabilities, they may also present a new challenge for AI forensics algorithms for detection and attribution of synthetic media. In collaboration with digital forensic researchers participating in DARPA's SemaFor program, we curated a synthetic image dataset that allowed the researchers to test and val…

> It's important to see this sort of thing happening more and more. Why? If we insist on the authenticity of images, this is holding on to the old status quo in the same way we apply book and record copyright to digital content. We don't allow what the tech enables to the fullest, but we restrict it by pressing it into the old mold (e.g. by using DRM to make music a commodity). I think "photographic proof" is a histo…

> but I believe society will adapt quickly

What gives you this impression? How exactly do you believe society would adapt?

Post reply on HN