I, like many others most likely, thought this was gonna be a cool way to present your resume, or someone with a demo of theirs in Unreal Engine... Still, I was not disappointed by the plugin.
UnrealCV
21–30 of 47 posts
Re: UnrealCV
#22I thought about something like this for autonomous cars. The game engine could simulate all the sensors in a car. Then it would be possible to use this as training data. Would be fun to create a racing game out of it to let different algorithm compete against each other. Does this already exist? Google should have something like this, but probably not freely available.
AdasWorks is doing this, check the videos 'Data Generation Tool - Annotation' and 'Real-time Data Simulator' towards the bottom of this article (text is in Hungarian):
http://index.hu/tech/2016/09/13/obudan_epul_az_autoipar_noki...
Re: UnrealCV
#23I was hoping that this would be someone's really cool resume, but this is interesting, nonetheless.
I don't mean to criticise you personally, because I have done the same thing, but: Comments about what someone thought the title meant are very common and not interesting in any way.
Re: UnrealCV
#24This is a great example of how we (collectively) are using virtual worlds as "dreams" for Deep learning. In the Deep Vision world we as a group are trying to segment, classify and reinforce our NN training on labeled real world data. The challenge is, it's a very manual process to label data - specifically images. The more that we can do inside the computer, for example automatically labeling pixels inside an image,…
In order to transfer learnings from virtual worlds to the real world more efficiently, I imagine a module that translates real world footed to an abstract representation that is the same as for rendered footage.
In other words, you would train a NN on input from a footage of a walkthrough of a real building to output rendered footage from the same path (3D data from architects is already there). The middle layer of this quasi autoencoder then is the basis to train fully simulated tasks, e.g. autonomous vehicles. In a way, it would be similar to colorization of b/w footage. Would that scale training data?
Re: UnrealCV
#25This is a great example of how we (collectively) are using virtual worlds as "dreams" for Deep learning. In the Deep Vision world we as a group are trying to segment, classify and reinforce our NN training on labeled real world data. The challenge is, it's a very manual process to label data - specifically images. The more that we can do inside the computer, for example automatically labeling pixels inside an image,…
I was surprised, since I didn't think it would be realistic enough for this purpose, but Grand Theft Auto V is being used in this manner to train self-driving cars.
https://www.technologyreview.com/s/602317/self-driving-cars-...
Re: UnrealCV
#26Does anybody know if there's a plugin for unreal, like this, but supports creating geometry inside the game?
If not, is there a way of generating levels with code?
Re: UnrealCV
#27Aww, I don't get to create a walkthrough of my resume in Unreal? I'd love to let recruiters shoot my bosses. (nevermind that the last Unreal I played was in 1998.)
Hahaha thought the same, some kind of 3d-ish resume.
Re: UnrealCV
#28This is a great example of how we (collectively) are using virtual worlds as "dreams" for Deep learning. In the Deep Vision world we as a group are trying to segment, classify and reinforce our NN training on labeled real world data. The challenge is, it's a very manual process to label data - specifically images. The more that we can do inside the computer, for example automatically labeling pixels inside an image,…
I find this incredibly interesting. Do you have any more information on the subject you can point me to?
Re: UnrealCV
#29This is a great example of how we (collectively) are using virtual worlds as "dreams" for Deep learning. In the Deep Vision world we as a group are trying to segment, classify and reinforce our NN training on labeled real world data. The challenge is, it's a very manual process to label data - specifically images. The more that we can do inside the computer, for example automatically labeling pixels inside an image,…
I find this incredibly interesting. Do you have any more information on the subject you can point me to?
Best thing is to probably search around for "Synthetic Training"
Here are two examples of some of the research done in this area:
http://www.cv-foundation.org/openaccess/content_iccv_2015/pa...
Re: UnrealCV
#30This is a great example of how we (collectively) are using virtual worlds as "dreams" for Deep learning. In the Deep Vision world we as a group are trying to segment, classify and reinforce our NN training on labeled real world data. The challenge is, it's a very manual process to label data - specifically images. The more that we can do inside the computer, for example automatically labeling pixels inside an image,…
In order to transfer learnings from virtual worlds to the real world more efficiently, I imagine a module that translates real world footed to an abstract representation that is the same as for rendered footage. In other words, you would train a NN on input from a footage of a walkthrough of a real building to output rendered footage from the same path (3D data from architects is already there). The middle layer of t…
Yea, I mean that is basically what we do with our home furnishings app - except we have to SFM to build the models.
The challenge is labeling - or autolabeling pixels.
One thing we are trying to work out is how do you label and build nets on volumes - rather than just pixels? I'm thinking it's going to be a magnitude harder.