[levesque]

There's probably a project to make here. Take those pixel2pixel models that are able to generate images from drawings, generalize them to 3D, say a pixel2vertex. Would be pretty neat.

The key would be to find a way to constrain the output space so that it's not so vast that it won't be possible to converge to something useful.

[azlen]

That would be very interesting, reminds me of an demo a couple years back of sketching buildings and and immediately being translated using procedural shape grammars into 3d.

http://www-sop.inria.fr/reves/Basilic/2016/NGGBB16/