Blade Runner re-encoded using neural networks
1–10 of 70 posts
Re: Blade Runner re-encoded using neural networks
#2As mentioned, there is likely no legal precedent regarding this type of video creation resulting from AI. We will have to watch how the first cases are presented by the original owners of the content to see which methods they will use to hinder this sort of "recreation."
-- Sam Smith Web Developer and Aspiring Chef~ Large file transfers made easy. www.innorix.com/en/DS
Re: Blade Runner re-encoded using neural networks
#3Can anyone explain what does this encoder actually does and how is it different than any other encoder?
The article almost seems to make it sound that this encoder somehow reconstructed the film...
Re: Blade Runner re-encoded using neural networks
#4Can anyone explain what does this encoder actually does and how is it different than any other encoder? The article almost seems to make it sound that this encoder somehow reconstructed the film...
I believe it's similar to Google's deep dreaming created images, but with videos.
Re: Blade Runner re-encoded using neural networks
#5Can anyone explain what does this encoder actually does and how is it different than any other encoder? The article almost seems to make it sound that this encoder somehow reconstructed the film...
I believe it's similar to Google's deep dreaming created images, but with videos.
This technique is quite different from deep dream. An autoencoder is a model that is trained to compress then reconstruct an image. After seeing and trying to reconstruct many images, it learns how to make a "compressed representation" from original images by going through this compress -> uncompress scheme, which typically results in blurry/lossy reconstructions of images which are very different than the normal artifacts we see in lossy compression schemes like jpg, etc.
In deep dream, a network whose goal is to predict image categories is "run in reverse" and used as a generative model, but it was not intended to be generative from the outset. Many times autoencoders are intended to be generative, or at least learn relationships between images (sometimes called a latent space/latent variable), where classification tasks care more about just getting the classification correct - no explicit concern on learning relationships between categories/images in those groups.
Re: Blade Runner re-encoded using neural networks
#6Earlier quoted context omitted.
I believe it's similar to Google's deep dreaming created images, but with videos.
This technique is quite different from deep dream. An autoencoder is a model that is trained to compress then reconstruct an image. After seeing and trying to reconstruct many images, it learns how to make a "compressed representation" from original images by going through this compress -> uncompress scheme, which typically results in blurry/lossy reconstructions of images which are very different than the normal art…
Would it be possible to make it look better or even the same by increasing digits per frame (eg 1000 instead of 200)?
Re: Blade Runner re-encoded using neural networks
#7As mentioned, there is likely no legal precedent regarding this type of video creation resulting from AI. We will have to watch how the first cases are presented by the original owners of the content to see which methods they will use to hinder this sort of "recreation." -- Sam Smith Web Developer and Aspiring Chef~ Large file transfers made easy. www.innorix.com/en/DS
Just guessing but the downvotes may be due to the 'sig' you've included coming across as spammy. You might notice that no one else here is doing that, and it likely isn't a good way to encourage interest in your product. How about submitting a post where you discuss some of the problems you've solved?
Re: Blade Runner re-encoded using neural networks
#8Earlier quoted context omitted.
This technique is quite different from deep dream. An autoencoder is a model that is trained to compress then reconstruct an image. After seeing and trying to reconstruct many images, it learns how to make a "compressed representation" from original images by going through this compress -> uncompress scheme, which typically results in blurry/lossy reconstructions of images which are very different than the normal art…
Would it be possible to make it look better or even the same by increasing digits per frame (eg 1000 instead of 200)?
Yes, technically yes. Although I'd say this is not what this experiment aims to.
In the future we may be able to colouring b/w movies and increase fps via this automatic software.
Re: Blade Runner re-encoded using neural networks
#9But no audio, right?
So, you'd think that alone would be a strong indicator that there was no intent (or capacity) to profit from the reconstructed version.
Re: Blade Runner re-encoded using neural networks
#10Earlier quoted context omitted.
Would it be possible to make it look better or even the same by increasing digits per frame (eg 1000 instead of 200)?
Yes, technically yes. Although I'd say this is not what this experiment aims to. In the future we may be able to colouring b/w movies and increase fps via this automatic software.
The future is now! [0,1]