Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

3D Face Reconstruction from a Single Image

cs.nott.ac.uk

Post reply on HN
Print view View original

1–10 of 47 posts

Re: 3D Face Reconstruction from a Single Image

#3

Post by M4v3R »

mistaken wrote: post #2

I wonder whether this could be used to crack face id.

Probably not. Apple specifically said that they've tested Face ID against masks (even Hollywood quality ones). Also, Face ID checks for user attention, so a static 3d-printed would not work. I wonder though if it worked if you put a mask over your face with eye cutouts? When the devices arrive I'm pretty sure some very clever people will try to tackle this problem, this should be interesting :)

Re: 3D Face Reconstruction from a Single Image

#4

Post by hughes »

It definitely constructs a face, but how accurate is it?

Would be interesting to see a measurement of error against a known result. Maybe try rendering an image of a 3d model of a face, then attempt to reconstruct it from the rendered image and measure the displacement from the original model.

Re: 3D Face Reconstruction from a Single Image

#5

Post by tw1010 »

M4v3R wrote: post #3
mistaken wrote: post #2

I wonder whether this could be used to crack face id.

Probably not. Apple specifically said that they've tested Face ID against masks (even Hollywood quality ones). Also, Face ID checks for user attention, so a static 3d-printed would not work. I wonder though if it worked if you put a mask over your face with eye cutouts? When the devices arrive I'm pretty sure some very clever people will try to tackle this problem, this should be interesting :)

Man are they good at marketing. They just knew this precise conversation would come up and created the perfect brief counter-argument preemptively ("hollywood quality masks").

Re: 3D Face Reconstruction from a Single Image

#6

Post by bd »

Had some fun with it yesterday :)

http://alteredqualia.com/xg/examples/facial_expressions.html

http://alteredqualia.com/xg/examples/max_headroom.html

It seems to be working pretty well, results do look nicer than earlier methods which were based on morphable faces [1][2].

See also continuous face reconstruction from video on their project page [3].

------

[1] https://www.youtube.com/watch?v=nice6NYb_WA

[2] http://gravis.dmi.unibas.ch/publications/Sigg99/morphmod2.pd...

[3] http://aaronsplace.co.uk/papers/jackson2017recon/

Re: 3D Face Reconstruction from a Single Image

#8

Post by andreyk »

Note that this is just one recent work in a well established research problem that has been worked on for decades. The interesting bit here is that they appear to achieve state of the art results by doing something simpler than other approaches - instead of fitting a well thought out generic morphable face model, they use a pretty standard deep learning model to map a 2d image to a discretized 3d model of the face (voxels). Intuitively this feels a bit off, since outputting a discretized 3d model instead of fitting a continuous model has inherent resolution limitations, but the benchmark results are pretty impressive.

Re: 3D Face Reconstruction from a Single Image

#9

Post by blt »

andreyk wrote: post #8

Note that this is just one recent work in a well established research problem that has been worked on for decades. The interesting bit here is that they appear to achieve state of the art results by doing something simpler than other approaches - instead of fitting a well thought out generic morphable face model, they use a pretty standard deep learning model to map a 2d image to a discretized 3d model of the face (v…

Maybe it is comparatively easy to fit the morphable model to the voxels?
Post reply on HN