[x3d-public] Computer Graphics "truth" data for learning vision.

[John Carlson]

So computer graphics takes geometry/shapes and produces video.

Computer vision takes videos and produces geometry/shapes.

Can we take the computer graphics input and output data and help out the 
computer vision people?

That is, output data from computer graphics is input to computer vision, 
and the neural network is trained to produce computer graphics input data.

Google: geoffrey hinton GLOM

John