Frame is not the same... look at left arm (picture left not his left).. bicep area jacket crease... also if you overlay them on each other the facial expression is slightly diff too
Came here to say exactly what you said in both comments. Only thing I could add is the eyes look slightly off.... but in a way I actually think would support deep fake theory.
The lighting difference also makes it hard to tell.
The biggest issue I have is that look at what hollywood can do with deep fakes... now you know the deep state has more advanced tech than that... why make an obvious deep fake? Thats what Im trying to wrap my head around now. If it is a fake... why?
Whoa holy shit, this is kinda nutso. I was on the "this is real" train before but I'm now leaning toward the "this is deep fake" train.
So a real person doesn't make nearly the same face twice, but DNNs do because their training dataset is finite and it doesn't learn in real-time to identify it already used a pose.
(also NN wizards please don't pick me apart here; I know that's not how it works exactly, but my point I'm trying to get across is it's not like an LSTM: the network has no feedback to prevent over-reliance on a particular learned concept over time)
Frame is not the same... look at left arm (picture left not his left).. bicep area jacket crease... also if you overlay them on each other the facial expression is slightly diff too
In deep fakes you typically have a real actor that get's a face superimposed that would explain any difference below the head
I didnt say it wasnt a deep fake I said its not the same frame
Came here to say exactly what you said in both comments. Only thing I could add is the eyes look slightly off.... but in a way I actually think would support deep fake theory.
The lighting difference also makes it hard to tell.
The biggest issue I have is that look at what hollywood can do with deep fakes... now you know the deep state has more advanced tech than that... why make an obvious deep fake? Thats what Im trying to wrap my head around now. If it is a fake... why?
Whoa holy shit, this is kinda nutso. I was on the "this is real" train before but I'm now leaning toward the "this is deep fake" train.
So a real person doesn't make nearly the same face twice, but DNNs do because their training dataset is finite and it doesn't learn in real-time to identify it already used a pose.
(also NN wizards please don't pick me apart here; I know that's not how it works exactly, but my point I'm trying to get across is it's not like an LSTM: the network has no feedback to prevent over-reliance on a particular learned concept over time)