#Deepfakes are everywhere, but #DigitalForensics investigators are fighting back:

[deixis9@beige.party]

@FabMusacchio @spellingmistakescostlives

[castrillo@mastodon.online]

@FabMusacchio good post

[jonnyt@mastodon.me.uk]

@NatureMC @ilusenn @FabMusacchio Definitely not a fan either but I am aware of where this one leads (or, at least, should).

[mourioche@mastodon.social]

@mathieu_ @AudeCaussarieu Je mets ma main au feu que les IA génératives savent déjà le faire, si on leur demande dans le prompt

On va surement en arriver au même résultat que pour la presse ou la télévision : La confiance dans le média sera lié à la réputation du média et à rien d'autre...

[leah@blahaj.social]

@f4grx @FabMusacchio sun rays are parallel, yet they meet at a point...?

[fuzzy@beige.party]

@Deixis9 what's the origin of the image?

Thanks

I see that it's commercialised e.g. <https://lovingsquad.com/product/ai-slop-is-not-art-chatbots-are-not-your-friends-shirt/>, <https://pagtee.com/product/t-shirt/1926944-ai-slop-is-not-art-chatbots-are-not-your-friends-cyborg-painting-flames>, <https://zerevia.com/product/t-shirt/1926944-ai-slop-is-not-art-chatbots-are-not-your-friends-cyborg-painting-flames>, <https://www.spellingmistakescostlives.com/product-page/copy-of-ai-slop-is-not-art-chatbots-are-not-your-friends-sticker>, however there's no real acknowledgement of an original artist; no credit, as far as I can tell.

@FabMusacchio @spellingmistakescostlives

[ncrazed@fd00.space]

@leah @f4grx @FabMusacchio they meet at such a far away point that they appear to be parallel

[mabande@mastodon.social]

@microblogc @FabMusacchio Forced perspective is your friend: "The Potemkin Stairs in Odesa extend for 142 metres, but give the illusion of greater depth since the stairs are wider at the bottom than at the top."

[leah@blahaj.social]

@nCrazed @f4grx @FabMusacchio But this is irrelevant for the technique described? It would work with a non-parallel spot lamp just as well?

[ncrazed@fd00.space]

@leah @f4grx @FabMusacchio yeah, I think that's a fair criticism

[mansr@society.oftrolls.com]

@nCrazed @leah @f4grx @FabMusacchio Lines from a shadow through the object casting it meet at the light source. Sunlight being virtually parallel is irrelevant. If the light source isn't point-like, you get blurry shadows.

[deixis9@beige.party]

@fuzzy @FabMusacchio @spellingmistakescostlives

https://www.spellingmistakescostlives.com/drawings

[mansr@society.oftrolls.com]

@nCrazed @leah @f4grx @FabMusacchio If the light source is behind the image plane, these lines will of course converge at an opposite point. The important part is that they all converge. If they intersect every which way, something funny is going on.

[ragon2@mstdn.social]

@FabMusacchio Great to have a sure way to prove things, but honestly, just zoom in on details see if they're coherent? In most if not any genai image? Not even talking about the dinausore/crocodile one because if you're under 50 you could tell in one blink

[mcwabbit@tenforward.social]

@FabMusacchio Also the soldiers’ heads in the first picture are nearly identical and their tags are gibberish.

[f4grx@chaos.social]

@mansr @nCrazed @leah @FabMusacchio yep I agree with that remark, modulo lens distortions. I would love to see the actual convergence on a known good image, for comparison sake.

[leah@blahaj.social]

@f4grx @mansr @nCrazed @FabMusacchio I tried it on two random hallway images from Kagi Search and it worked great. I think most lens distortions are nonlinear, so the problem is rather that the lines are not straight than that they won't meet.

[f4grx@chaos.social]

@leah @mansr @nCrazed @FabMusacchio How do you model the curvatures of these non straight lines so you can be sure that they all meet at the same point?

[leah@blahaj.social]

@f4grx @mansr @nCrazed @FabMusacchio I didn't need to, since the lines were straight I assumed lens correction was already done or not necessary.

[octaviaconamore@cutie.city]

@FabMusacchio @Jenetrix I feel like I'm in a Realism 101 illustration class