Image-to-Image Translation with Conditional Adversarial Nets
phillipi.github.io
Image-to-Image Translation with Conditional Adversarial Nets
1–10 of 61 posts
Re: Image-to-Image Translation with Conditional Adversarial Nets
#2I wonder how well this scales to a larger domain of interest. So, e.g., if the neural net needs to know not only about cars and nature, but about more topics such as people, faces, computers, gastronomy, santa claus, halloween, etcetera, how does the neural net scale? And how should its topology be extended under such scaling?
Re: Image-to-Image Translation with Conditional Adversarial Nets
#3This is awesome!
Makes me wonder how this can apply to image and video compression. You could send over the semantic segmentation version of an image or video, and system on the other end would use these technique to reconstruct the original.
Re: Image-to-Image Translation with Conditional Adversarial Nets
#4The "sketches to handbags" example, which is buried toward the bottom, is really cool. It's basically an extension of the "edges to handbags," but with hand-drawn sketches.
Even though the sketches are fairly crude, with no shading and a low level of detail, many of the generated images look like they could, in fact, be real handbags. They still have the mark of a generated image (e.g. weird mottling) but they're totally recognizable as the thing they're meant to be.
The "sketches to shoes" example, on the other hand, reveals some of the limitations. Most of the sketches use poor perspective, so they wouldn't match up well with edges detected from an actual image of a shoe. Our brains can "get the gist" of the sketches and perform some perspective translation, but the algorithm doesn't appear to perform any translation of the input (e.g. "here's a sketch that appears to represent a shoe, here's what a shoe is actually shaped like, let's fit to that shape before going any further"), so you end up with images where a shoe-like texture is applied to something that doesn't look convincingly like a real shoe.
Re: Image-to-Image Translation with Conditional Adversarial Nets
#5I feel this can potentially revolutionize creative processes, for example in the clothing industry. You just draw up a purse or a shoe, let the machines generate dozens of variants (with pictures), and then you only have to filter and rank them.
You can pipe these product sketches directly into focus groups who tell you which product is most likely to sell. You don't need massive staff to come up with product variants any more.
Re: Image-to-Image Translation with Conditional Adversarial Nets
#6Interesting.
What I like about the "Day to Night" example is that is clearly demonstrates that these sort of networks lack common sense. It expects light to be where they are clearly (to humans with common sense at least) no things that can produce light. E.g. in the middle of a roof or in a tree. Of course, there can be, but it's fairly uncommon.
And the opposite as well, no lights where a human would totally expect a light, eg. in the front of buildings or on the top of, well, lighting poles.
Re: Image-to-Image Translation with Conditional Adversarial Nets
#7I feel this can potentially revolutionize creative processes, for example in the clothing industry. You just draw up a purse or a shoe, let the machines generate dozens of variants (with pictures), and then you only have to filter and rank them. You can pipe these product sketches directly into focus groups who tell you which product is most likely to sell. You don't need massive staff to come up with product variant…
It has the potential to redefine what we think of as 'creativity', as happened with what we consider intelligence and what we think of as "AI Hard" problems.
Perhaps what these networks are generating can be labeled better as "Guided/constrained imitation" rather than real creativity.
Re: Image-to-Image Translation with Conditional Adversarial Nets
#8Besides a cool new application of GANNs, I don't see if this architecture is much different than normal GANNs. Anyone else have thoughts?
Re: Image-to-Image Translation with Conditional Adversarial Nets
#9I feel this can potentially revolutionize creative processes, for example in the clothing industry. You just draw up a purse or a shoe, let the machines generate dozens of variants (with pictures), and then you only have to filter and rank them. You can pipe these product sketches directly into focus groups who tell you which product is most likely to sell. You don't need massive staff to come up with product variant…
It has the potential to redefine what we think of as 'creativity', as happened with what we consider intelligence and what we think of as "AI Hard" problems. Perhaps what these networks are generating can be labeled better as "Guided/constrained imitation" rather than real creativity.
> real creativity
What is real creativity? Creativity is just random noise converted into patterns. Is the computer variety of creativity not real enough?
Re: Image-to-Image Translation with Conditional Adversarial Nets
#10Earlier quoted context omitted.
It has the potential to redefine what we think of as 'creativity', as happened with what we consider intelligence and what we think of as "AI Hard" problems. Perhaps what these networks are generating can be labeled better as "Guided/constrained imitation" rather than real creativity.
> real creativity What is real creativity? Creativity is just random noise converted into patterns. Is the computer variety of creativity not real enough?
> Creativity is just random noise converted into patterns.
This is not a consensus definition. Creativity doesn't actually seem to be very random at all according to the people who study it.