Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Deep Convolutional Inverse Graphics Network

willwhitney.github.io

Post reply on HN
Print view View original

21–24 of 24 posts

Re: Deep Convolutional Inverse Graphics Network

#21

Post by tejask »

rirarobo wrote: post #17

Very cool work, I'm happy to see more people thinking about deep networks along these lines. It seems that this is very similar to a recent work put on arxiv back in November, "Learning to Generate Chairs with Convolutional Neural Networks". http://arxiv.org/abs/1411.5928 They also have a very cool video of the generation process: https://youtu.be/QCSW4isBDL0 It's very interesting to see two groups independently deve…

thanks for the references! I like that many people are doing such things. After looking at the chairs paper, it seems like they render images given pose,shape,view etc (supervised setting). However, in our model, there is a twist as it is trained either completely unsupervised or biased to separate those variables (but it is never given the true values of those parameters ... just raw data).

Re: Deep Convolutional Inverse Graphics Network

#22

Post by tejask »

jwp729 wrote: post #20
tejask wrote: post #15

Earlier quoted context omitted.

there are many ways to parametrize the decoder. One of the ways is to constrain it to output an explicit mesh or volumetric representation and express the rendering pipeline so that it's differentiable. The encoder will then effectively learn an "inference algorithm" to get the best output. A feedforward neural network is not enough and recurrent computations will eventually be necessary.

Can you explain a bit more why the recurrent network structure becomes necessary at some point? Is that because reversing a CNN naturally means rendering by (de)convolution?

In order to approximately learn a "real" graphics engine with support for basic physics, just feed-forward computation might not be sufficient. A more natural way to learn graphics/physics might be to learn the temporal structure more explicitly. On the other hand, it might also be interesting to just add temporal convolution-deconvolution structure in the existing model. This is work in progress though.

Re: Deep Convolutional Inverse Graphics Network

#23

Post by tejask »

amelius wrote: post #14

So, in essence, this network can learn to "unproject" images. Since projection is a lossy operation, a projected image has potentially multiple inverses. And this makes me wonder how this system deals with the situation where two or more inverses exist and are equally likely.

This is an interesting question. Technically, we capture a probability distribution in the code layer (between encoder and decoder). So you can sample from it multiple times and assess uncertainty. However, we have not really studied this.
Post reply on HN