[xmichael999]

These libs assume the angle is the same, i.e. square shot of the face. Cameras mounted up high are completely useless with these types of libs. Unless the tech. exists to magically rerender a front face shot so you can image how it would look from 12 - 20 feed raised up, this doesn't work.

[johnrbent]

Paid for by the same IARPA contract as dlib: https://talhassner.github.io/home/projects/frontalize/hassne...

[MertsA]

That might be an interesting problem for a generative adversarial network. Train it based on some large corpus of faces and then refine it based on searching for the input vector that most closely matches the original image and then just change the pose in that input vector to generate a square shot of the face. In theory this would give you not only some generated face, but some reasonable space of facial features that the discriminator couldn't reject. I.e. beard / no beard if the chin was obscured.

[mbrumlow]

I wonder what happens if we take a square shot of a face, then use something like the deep fakes to generate different predicted views and then feed those in to the original system.

[ars]

You get Omphaloskepsis.

[mbrumlow]

Is this really a thing? Man, you learn something every day... I am not sure I needed to know about this though :/