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

[Joseph D Williams]

➢ So computer graphics takes geometry/shapes and produces video.
➢ Computer vision takes videos and produces geometry/shapes.

All that is needed is the common context and ontology to transcode between the representations. 
Figure out the style sheet, maybe as you go, then see what might appear from the media you sample and what might manifest in the space you are building. 




From: John Carlson
Sent: Friday, April 23, 2021 9:15 PM
To: X3D Graphics public mailing list
Subject: [x3d-public] Computer Graphics "truth" data for learning vision.

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


_______________________________________________
x3d-public mailing list
x3d-public at web3d.org
http://web3d.org/mailman/listinfo/x3d-public_web3d.org

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://web3d.org/pipermail/x3d-public_web3d.org/attachments/20210424/96604b4f/attachment.html>