584
Robot dogs with heads of Elon Musk and Mark Zuckerberg roam San Francisco streets (www.dexerto.com)
submitted 6 months ago by to c/nottheonion@lemmy.world
88 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 6 points 6 months ago* (18 children)

I realize there are amazing artists with great sculpting skills. But these faces do look like they were made from real face moulds.

Which makes me wonder.

  1. Musk and Zuck agreed to have a mould of their face.
  2. Only these two fools could afford these robot dogs.
  3. Musk already developed remote robot tech.

Conclusion. They both are behind the stunt.

There was a tesla humanoid robot a while back with musks face.

Dude. It's likely them running these robots. Remotely.

Cause they can't go out in public. Cause of the angry mobs.

  • permalink
  • fedilink
  • source
  • hideshow 18 child comments
    •
  • [–] 7 points 6 months ago (8 children)

    Using AI to create a 3D mold from a few photos?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 8 child comments
    •
  • [–] 2 points 6 months ago* (7 children)

    Yeah the 3d ai is no where at that level.

    Only way to make a good 3d model is 3d scan. You can do that with a regular camera or a fancy scanner. The real work (compiling images) is done on the software.

    Still requires person to agree. It takes at minimum 100 photos to get a good model.

    But even with a 3d model, you'd have to make a 3d print. Resin would be most accurate. Not filament.

    Printed to scale.

    Then turn that into a mould. Because you can't use resin moulds.

    Then make a support shell mould. Which you would need to make even if mould was made directly from face but it's way easier to do it from a real face. Plus you get fine lines and pores. If you have a really high resolution silicone.

    Then also someone skilled, painted it and hand added hair. Each strand is manually added. You can buy hair patches but it looks directly added. Like how it's done on high end doll heads. (But most cheap toy dolls use machines that add clumps at a time. Not single hair. or sew the hair on.)

    These must have been incredibly expensive to produce.

    Well, expensive for you or me.

    Maybe 5k for a head. Assuming a few heads were made. That's what I would guess knowing the labor and materials involved.
    If only one head. Maybe more. Since mould making process is expensive.

    $6k or 7k maybe? Also more because of the NDA.

    Assuming that musk or zuck are the ones commissioning these.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] 2 points 6 months ago (4 children)

    Nobody ever made sculptures before that.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 6 months ago (3 children)

    Not a single 3D printer or scanner was used for Lord of the rings.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 1 point 6 months ago (2 children)

    Yeah traditionally, real faces are used to make moulds.

    Then for fx stuff, the sculptist uses a cast model of the face to make the fx latex pieces of masks or whatever to fit on that person's face.

    High quality ones , anyway. When it's tailored for the persons face it fits better and looks better.

    There are a ton of videos on how this is all done. I always liked watching videos on movie magic. So that's how I know the basics.

    But I can say that almost always, when a likeness of someone is needed, they make the prop from making moulds from the actual person's face.

    That's the best source.

    3d printing itself , introduced artifacts and errors. So it's not really the best medium.

    Even madame tussauds waxworks starts with moulds made from the people's faces (people who are alive anyway).

    Fun fact. Michael Myers from Halloween movies wears a William Shatner latex mask. Made from a cast of his face.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 4 points 6 months ago (1 child)

    Na, there are great artists out there with a sense for details. Check out Bobby Fingers youtube channel for instance. https://www.youtube.com/channel/UCXKCiTquPMavBqgXgrM9mBg He usually make dioramas with (a ridiculous) commentary, but one time he made Jeff Bezos head as a rowing boat.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 6 months ago (6 children)

    You can generate a 3D image of a head with enough pictures of that stupid head.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 1 point 6 months ago (5 children)

    These AI generated 3d models from a few images are not very good. As I said the renders look kinda ok. But you pull up the actual mesh and they are garbage.

    Do do a legit good scam you have to take a ton of photos from multiple heights , 360 degrees. And make sure the lighting is good and there is a solid back drop so the software can tell what to model.

    Here is an example of what I mean. It's called photogrammetry.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 2 points 6 months ago*

    I think that the technology may have evolved a lot since the early days of photogrammetry, or perhaps making a 3D model of a face is easier than a large object like in your example. Also, how do you suppose they got 3D scans of Picasso's and Warhol's faces for those perfect, life-like rubber faces on that video? They were both dead decades before the development of 3D scanning and photogrammetry.

    Finally, here are some examples of photo to 3D model applications that appear to only need one photo:

  • permalink
  • fedilink
  • source
  • parent
  • [–] 1 point 6 months ago (3 children)

    These AI generated 3d models from a few images are not very good.

    They actually are. You can iteratively correct them.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 1 point 6 months ago (2 children)

    They really aren't. I actually make 3d models.

    The only half ass decent ai ones are ones that are basically copies of other 3d designs made from humans to the point you can barely tell them apart. Cause it's just a copy.

    These ads for ai 3d models are false.

    They are poor.

    So part of making 3d model assets is that the mesh is wrapped in a map.
    Think of a globe wrapped in paper of a map of the earth.

    Doing this allows for a much lower mesh triangle. Lower poly. But it can give the impression it's higher because the wrap is from actual images and is upscaled.

    So render images look high quality but the actually aren't. It's the wrap.

    Here is an example. You 3d scan a chocolate Santa. In foil. All the little wrinkles in the foil and details look like they were captured. But it's not actually true. The wrap makes it look like it's a high quality mesh. But it's just a blob shape. It doesn't actually contain wrinkles or texture.

    It's all just the wrap. This sort of process is great for making digital assets. It makes low poly realistic items. But it's garbage for making 3d prints.

    I'm going to reply to this with another image that shows this in relation to 3d printing.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 6 months ago* (last edited 6 months ago) (1 child)

    Here is a phot of the ai 3d render which looks realistic.

    To the 3d print model. Which shows most details are missing. Almost like it was clay and smoothed out.

    The details are only there from the uv map wrap.

    They aren't actually on the model mesh.

    There are other rendering tricks you can do to make textures in wraps look "3d" . But it's not really 3d. It's flat surface wraps.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •