I have heard that profiles (i.e. side views) are super hard for deep fakes (at the moment at least) due to the in-filling required.
This does not seem to suffer from it from what I can see.
Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
21–30 of 37 posts
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#22"With the advent of AI, either we all go to prison or no one gets convicted, because everything can be fabricated." - me
AI replication of voices, deepfakes, etc...
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#23Part of me is morbidly curious about the possible chaos all this will be causing in 5 years. Maybe humanity can’t survive the mist this will bring.
It’ll be fine. Keep in mind that the world has run on handwritten signatures for a few hundred years. And anyone could say anything in a letter with no “pixels” to prove it right. Digital media as strong evidence has been a novelty. If anything the real thing to watch out for will be the echo of national digital ID. This would certainly solve the mild/moderate issues of deepfakes while (if done poorly) risking a seri…
I wonder if having all this "strong evidence" has caused us modern people to lose the social norms and relationships that people had to depend on back when human trust was more important. Like, good fences make good neighbors but what happens when all of a sudden the fences don't work anymore and we have to be good neighbors without them?
I'm guessing an uncomfortable transition period at least.
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#24Is there a technology we might use someday to prove the provenance of digital media? Like every video and photo has a blockchain entry or something. And any time there’s a modification, that gets recorded too. So in the future we might right click any random video and see its file history.
There has been attempts but they have fared poorly: https://petapixel.com/2011/04/28/nikon-image-authentication-...
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#25If you believe peoples necks don't contain a spine I guess you'd call this "hyperrealistic" ?
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#26Is there a technology we might use someday to prove the provenance of digital media? Like every video and photo has a blockchain entry or something. And any time there’s a modification, that gets recorded too. So in the future we might right click any random video and see its file history.
There's an attempt happening here: https://contentauthenticity.org/
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#27I see this "fake tom cruise" serie of video a lot on youtube (probably the same guy, because it's the same voice and same height). It's so perfect it made me wonder if the guy's isn't already a tom cruise lookalike and the AI part only adjusts minor details. Do we have a photo of the original content ?
Could be this guy
https://www.hollywoodreporter.com/business/digital/deepfake-...
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#28Was totally Uncanny Valley for me. There's no obvious flaw (on the contrary, looks great), but there's just something off between how his shoulders, neck, and head move.
You only feel like that because you know it's a deepfake beforehand. It's a real person, an actor with a swapped face, so whatever he's doing with the movement of his shoulders neck or head is completely natural.
...or maybe it actually does look awkward ?
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#29Wow, that looked incredible. It does worry me that you could generate a video about a celebrity / VIP in a compromising situation, and that it goes viral before anyone can disprove it. Alternatively, could there be a video scanner that tells you if the video has AI "fingerprints", and this would be built into social media platforms with a "likely AI generated content" warning on posts.
Re: Hyperrealistic Deepfaked Tom Cruise in a Coffeeshop
#30Wow, that looked incredible. It does worry me that you could generate a video about a celebrity / VIP in a compromising situation, and that it goes viral before anyone can disprove it. Alternatively, could there be a video scanner that tells you if the video has AI "fingerprints", and this would be built into social media platforms with a "likely AI generated content" warning on posts.
Or, we could just remove video/audio as evidence. Even with fingerprinting, it can still be faked enough to get past judged and elected folks who are already 200 years older than they should be while in office.
People are easily faked and, imho, it’s safest to assume everything is faked.