21–30 of 47 posts
Earlier quoted context omitted.
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").
Is it good marketing or engineering (the latter implies both)? I guess we'll find out soon enough.
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?
-----
Here is the same image used as input for 3d face reconstruction using both methods:
Left side is morphable face model (EOS by Patrik Huber).
Right side is this new CNN voxels method.
-----
Here is live 3D model on the authors' site:
http://www.cs.nott.ac.uk/~psxasj/3dme/view.php?name=../59b41...
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.
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.
It's fitting faces to some kind of assumed model. I tried it on a few Japanese faces; it basically gave them a Caucasian-looking side profile: big foreheads with over-hanging eyebrow ridges; big noses. Completely unrecognizable after turning more than a few degrees from front view. Which is not to flame the project---nice work!---but as a potential improvement for certain applications, it would be useful to simply ha…
Earlier quoted context omitted.
If you look at the .obj model file that you can download you can see exactly how accurate it it. The mesh is dense and the detail is not. The detail that it does have however is very plausible.
One of the authors here. You are very right in saying that the there aren't many details. This limitation, we believe, is due to a lack of large, high quality training sets. The data we trained from was very smooth, which means our method is unable to pick out features such as wrinkles and dimples.
Earlier quoted context omitted.
> static 3d-printed would not work right, but adding in fake eyeballs should do the trick. For inspiration, check out how these guys fool Samsung's iris scanner: https://www.youtube.com/watch?v=4VrqufsHpS4
They mentioned an infrared camera, bet they're checking temperature too.
Earlier quoted context omitted.
> static 3d-printed would not work right, but adding in fake eyeballs should do the trick. For inspiration, check out how these guys fool Samsung's iris scanner: https://www.youtube.com/watch?v=4VrqufsHpS4
They mentioned an infrared camera, bet they're checking temperature too.
Earlier quoted context omitted.
One of the authors here. You are very right in saying that the there aren't many details. This limitation, we believe, is due to a lack of large, high quality training sets. The data we trained from was very smooth, which means our method is unable to pick out features such as wrinkles and dimples.
What about the "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." approach for generating high resolution training data?