You could use it to say, auto create large labeled data sets of images and their corresponding depth maps. Or generate large labeled data sets of objects and their segmentation masks. Or for training an autonomous agent (say self driving car) in a simulation environment
Exactly. That's the goal for this project.
Many thanks for your work, will be putting it to use! Please consider integrating it with https://gym.openai.com/ for easy reinforcement learning tasks.
Some similar efforts (though not with open source engines)
Yep, possibly. This approach has been successfully exploited in real-time SLAM for instance [1][2][3]
[1]http://link.springer.com/chapter/10.1007%2F978-3-642-33786-4... [2]http://www.doc.ic.ac.uk/~ahanda/VaFRIC/iclnuim.html [3]http://robotvault.bitbucket.org/
Is it so that computer vision researchers can create scenes in UE4 that can then be fed into their application?