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

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

nvidia-research-mingyuliu.com

Post reply on HN
Print view View original

41–50 of 52 posts

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#41

Post by dheera »

forgingahead wrote: post #38
dheera wrote: post #28

Earlier quoted context omitted.

It doesn't prevent discrimination, it just allows me to do what I want to do in the short term, e.g. raise funding for startups or get dream jobs or whatever. I mean if a VC hands me a term sheet or a hiring manager hands me a job and the ONLY thing I misrepresented is my face, I don't think they have any ethical grounds to retract their offer. Solving the discrimination problem is another matter, and will take years…

Sincerely, I'm sorry you feel that you haven't achieved certain things because of skin colour/accent/etc. However let me challenge that belief, only because if your assumption isn't true, that your lack of desired success is because of things outside of your control, then perhaps you won't make the adjustments potentially needed to actually achieve them. If your dreams truly cannot wait (as you said, and they shouldn…

Oh yes of course. I just think it would be a super cool technical project to actually make this work real time in a videoconference, and there would be lots of use cases for it. Eliminating survey biases during interview-style surveys is another.

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#42

Post by NavinF »

dheera wrote: post #36
batch12 wrote: post #35

Earlier quoted context omitted.

If you deceive someone by wearing a different face during an interview, I expect that you would not be hired. How do you prove you were the person interviewed?

There are plenty of ways to prove that, including stating a public key during the interview, interviewer signs it with their key, vice versa is done with the interviewer's key, and then the same is demonstrated in person with the same keys. Hell, how to do that can even be an interview question.

That's a terrible answer to the hypothetical interview question because your solution only works if the person that took the interview is not colluding with the person that wants the job. The interviewee could just email their private key to the job seeker.

The key signing only protects against some very uncommon threats

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#43

Post by midnitewarrior »

kadoban wrote: post #32
dillondoyle wrote: post #31

Earlier quoted context omitted.

It doesn't sound like they are trying to sell or somehow leverage to make profit? I guess 'develop new NVIDIA offerings' is kind of vaguely suspicious but the rest doesn't seem onerous to me unless I'm missing something?

Those license terms seem to me like they'd allow using someone's picture in unlimited advertising, for free. They also sound like they'll definitely be using them to train models. I wouldn't be surprised if some of that means they can sell them to advertisers for whatever nonsense.

My take is that they are limiting their liability in case anyone is overly letigius, or if they mishandle the data. Yes, they could do the things you describe, but my guess is they don't want to get sued by people they are providing a free service to.

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#44

Post by dahart »

koilke wrote: post #22

Inviting terms as usual: When you upload, submit, store, send or receive User Content to or through the NVIDIA Research AI Playground, you give NVIDIA (and parties NVIDIA works with, including its affiliates, suppliers and customers) a worldwide license to use (including without limitation for neural network training), host, store, reproduce, modify, create derivative works (such as those resulting from translations,…

The reason it’s usual is because all sites with upload features need the right to host what you upload. Facebook, for example, has the exact same thing.

“Permission to use content you create and share. [...] when you share, post, or upload content that is covered by intellectual property rights on or in connection with our Products, you grant us a non-exclusive, transferable, sub-licensable, royalty-free, and worldwide license to host, use, distribute, modify, run, copy, publicly perform or display, translate, and create derivative works of your content”

https://www.facebook.com/legal/terms

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#45

Post by pezezin »

dheera wrote: post #19
lwhi wrote: post #12

Earlier quoted context omitted.

I like faces. Why deny a key part of being human?

If you don't know why one might want this, you might be a white male, or at least white, or at least male, or at least a member of the majority race in your locality. I've definitely wanted this on a few occasions, to avoid being discriminated.

Why is everything about race nowadays?

Anyway, your comment is bullshit. I'm a white guy (actually from Spain, so I don't know if I qualify as "white" from the USA point of view) living in Japan, so I am the discriminated minority here (and yes, I have been a victim of minor racism), and I agree with GP. We humans evolved for face to face conversation, if racism is the problem, hiding behind a mask is not the solution.

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#46

Post by davbryn1 »

Seems to use the EXIF data to display the image, so if uploading an image from a portait image you might want to strip that or it breaks.

Its pretty cool, but one thing that always bugs me - why is the demo page so bad?

For the majority of people, this is the only way they are going to see this thing working - would it really have hurt to have had an actual frontend dev nock something together for this? It takes away from the great work behind the scenes imho

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#47

Post by thaumasiotes »

pezezin wrote: post #45
dheera wrote: post #19

Earlier quoted context omitted.

If you don't know why one might want this, you might be a white male, or at least white, or at least male, or at least a member of the majority race in your locality. I've definitely wanted this on a few occasions, to avoid being discriminated.

Why is everything about race nowadays? Anyway, your comment is bullshit. I'm a white guy (actually from Spain, so I don't know if I qualify as "white" from the USA point of view) living in Japan, so I am the discriminated minority here (and yes, I have been a victim of minor racism), and I agree with GP. We humans evolved for face to face conversation, if racism is the problem, hiding behind a mask is not the solutio…

> I'm a white guy (actually from Spain, so I don't know if I qualify as "white" from the USA point of view)

No, Spanish-speaking countries are considered nonwhite.[1] Portugal and France are both white; Spain not so much.

Brazil is a hazier issue.

(The reason is that Spanish speakers in the US don't tend to be Spaniards, and the laws were written in a sloppy way.)

[1] Technically, the "Hispanic" category is not supposed to be exclusive with the various race categories. But that is how it is treated.

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#48

Post by ycosynot »

If you allow me, about such animated pictures, you should be interested in my pet project -- 1000x animated(!) fantasy avatar faces. 100% AI-Generated. Check it out, it's free and beautiful, it feels like next-gen.

https://www.cgtrader.com/free-3d-models/character/fantasy/3d...

I made it shamelessly with https://www.fantasy-faces.com/ for the GAN and myheritage.fr for animation -- it was still a lot of work to select 1000 of the most beautiful.

Ultimately, I did it for the lulz...

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#49

Post by user-the-name »

pezezin wrote: post #45
dheera wrote: post #19

Earlier quoted context omitted.

If you don't know why one might want this, you might be a white male, or at least white, or at least male, or at least a member of the majority race in your locality. I've definitely wanted this on a few occasions, to avoid being discriminated.

Why is everything about race nowadays? Anyway, your comment is bullshit. I'm a white guy (actually from Spain, so I don't know if I qualify as "white" from the USA point of view) living in Japan, so I am the discriminated minority here (and yes, I have been a victim of minor racism), and I agree with GP. We humans evolved for face to face conversation, if racism is the problem, hiding behind a mask is not the solutio…

> Why is everything about race nowadays?

Because racism exists and is a real problem for lots of people.

You don't fix that by pretending race doesn't matter, because in the lived experience of all of those people, it matters, a lot. They would love it if it didn't matter, but that is not what happens in reality.

Re: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

#50

Post by lwhi »

dheera wrote: post #19
lwhi wrote: post #12

Earlier quoted context omitted.

I like faces. Why deny a key part of being human?

If you don't know why one might want this, you might be a white male, or at least white, or at least male, or at least a member of the majority race in your locality. I've definitely wanted this on a few occasions, to avoid being discriminated.

This is no solution.

What happens when you need to meet face to face?

Post reply on HN