How Deep Learning Networks Can Use Virtual Worlds To Solve Real World Problems; Forbes / Tech; Thursday 05 May 2016
Bringing virtual worlds into the picture
Modern game development engines have achieved a level of 3D realism that suggests an alternative approach to fulfilling the need for massive sets of training data. You can make your own virtual data instead of trying to acquire enough real data to train your network. Adrien Gaidon is doing just that.
Watch Adrien talking about this project on YouTube
CVPR2016: 'Virtual Worlds as Proxy for Multi-Object Tracking Analysis ' by Adrien Gaidon , Qiao Wang and Eleonora Vig.
Forbes / Tech | Thursday 05 May 2016
Read the article