ML turns video of a 360° turn into 3D model of a person

Link to the paper: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1803.04758" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1803.04758</a>

Oh how I hate marketing speech.<p>First of all, the title should include &quot;video of a predefined 360° turn&quot;.<p>And then they say something along the lines of &quot;average accuracy of about 5mm&quot; for joining the constructed modeled joints to their model, while you see the body wobbling around happily.<p>This is an impressive demo, but gah!

Structure from motion is an existing technique. What is the contribution of ML in this case (it seems like joint positioning maybe?)?<p><a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Structure_from_motion" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Structure_from_motion</a>

How is this ML? They use a CNN for foreground segmentation, a minor step in their pipeline. But the major contribution seems to be putting the silhouettes in a common reference frame. I sincerely hope sciencemag isn’t putting ML in the title purely to jump on the bandwagon.

As an artist, my first thought is <i>I wonder what happens if you try giving this a series of drawings</i>.

This is what should give you pause before using face authentication technology for anything.

I wonder if will see a future soon where a director can fully edit the positions and physical actions of the actors at post production.<p>basically, the whole scenes will be transferred to believable 3d models seemlessly, and you can reanimate parts of everything. I feel like that&#x27;s doing to happen for sure, for big Hollywood productions at least (like the Marvel stuff)

It seems determined to put visible toes on everybody, no matter that they&#x27;re wearing socks.<p>Is this a bug or a feature?

This is awesome. I wish someone will implement this as a piece of open source software. Imagine the potential!

Could be used for VR phone calls between long distance couples.