I would call "inverse graphics" a task. One can solve that task following different strategies. We demonstrate one way that uses RL and GANs and gives reasonably good results. For Omniglot, for example, there are works…
Yup, exactly! Btw, didn't realize those were your results (just mindlessly clicked on the link). Very cool stuff!
While it is true that one can simulate painting by search (in some sense), the problem is that (naive) search doesn't always work (we have an example in the paper). Moreover, training an agent has a benefit of fast…
You'd be surprised to see that both "inverse graphics" and "analysis-by-synthesis" are mentioned in the paper
The reason for that is that I chose a particular brush from the set of available brushes ('dry brush'). Since MNIST digits are quite sharp and opaque, the agent tries to achieve this by retracing the contours. I guess…
I would call "inverse graphics" a task. One can solve that task following different strategies. We demonstrate one way that uses RL and GANs and gives reasonably good results. For Omniglot, for example, there are works…
Yup, exactly! Btw, didn't realize those were your results (just mindlessly clicked on the link). Very cool stuff!
While it is true that one can simulate painting by search (in some sense), the problem is that (naive) search doesn't always work (we have an example in the paper). Moreover, training an agent has a benefit of fast…
You'd be surprised to see that both "inverse graphics" and "analysis-by-synthesis" are mentioned in the paper
The reason for that is that I chose a particular brush from the set of available brushes ('dry brush'). Since MNIST digits are quite sharp and opaque, the agent tries to achieve this by retracing the contours. I guess…