71–80 of 285 posts
Deepfake models are trained on very similar data. They don't generalize well, usually. E.g. we take lots of data from YouTube videos of a single person under a specific condition (same time, same day, same haircut etc.) I know that as I spent quite some time researching these models and worked on a deepfake detection startup. Purely looking at it from a technological side, it's a cat mouse game. Similar to an antivir…
> Put shoe on head
"profile view challenge" coming in 3, 2, 1 ...
Source: I work in the field. This is a current limitation, and an artifact of the data+method but not something that should be relied upon. If we do some adversary modelling, we can find two ways to work around this: 1) actively generate and search for such data; perhaps expensive for small actors but not well equipped malicious ones. 2) wait for deep learning to catch up, e.g. by extending NERFs (neural radiance fie…
One thing I notice with colorized movies is the color of the actor's teeth tends to flicker between grey and ivory. I wonder if there are similar artifacts with deep fakes.
I was recently looking for designers for my company when I came across an interesting profile on Dribbble. I reached out and quickly scheduled a time when we could talk over zoom. At the meeting time, in comes this person who seems to have a strange-looking, silicone-like face. I was using my Zoom account (I rarely use other peoples zooms unless I trust them), to avoid situations like this. One thing I noticed is tha…
For what it's worth, it looks more like an aggressive filter rather than a deepfake.
Serendipitously over the weekend I was thinking about a future where for key sensitive data access (e.g. production main) you may need to have a quick 5 minute call (4th factor, "3D verification") where you would be asked to turn on your camera and be asked to answer some simple question and in different positions... Main thinking was how out of control it would get, it would probably end up looking like anti-cheat s…
The only thing interesting about the title is the possibility of real time deepfakes for calls. If it's not realtime then 15years ago called and they want their technique back
I wonder how much work would it entail to swap one actor's face for another's in a movie. Just finished watching Fury Road, and Tom Hardy just feels a bit off to me.
That's "bread and butter" work in VFX. I used to be a stunt double actor replacement specialist. These daze, ML enhanced tools make the work for a face replacement shot exponentially faster and easier - as is needed for the huge number of superhero stunts insurance companies will not let the stars perform.
Earlier quoted context omitted.
No no... this does look like a proper downward dog, but no way you could do that!
Please say "I'm not a robot" with a Scottish accent 3 times and do a backflip to login.
Deepfake models are trained on very similar data. They don't generalize well, usually. E.g. we take lots of data from YouTube videos of a single person under a specific condition (same time, same day, same haircut etc.) I know that as I spent quite some time researching these models and worked on a deepfake detection startup. Purely looking at it from a technological side, it's a cat mouse game. Similar to an antivir…
> Put shoe on head
https://www.nytimes.com/2007/07/02/technology/02spam.html#:~...