How would this system colorize this image?: http://imgur.com/RBEht9H
Show HN: Open source colorizing grayscale images with NN
61–70 of 78 posts
Re: Show HN: Open source colorizing grayscale images with NN
#62Earlier quoted context omitted.
There might be a few scenes in between the viewings of the truck.
I'd imagine that many people wouldn't even notice (unless the truck's color is part of the plot)
Maybe it's about a truck painting shop, and every time they paint something, it either doesn't change color, or get a color different from what the customer ordered. I would watch that.
Re: Show HN: Open source colorizing grayscale images with NN
#63I wonder if this could be used to improve the proposed color prediction in Daala, or if the memory and CPU requirements are too high to put into a video codec.
Re: Show HN: Open source colorizing grayscale images with NN
#64These results: http://richzhang.github.io/colorization/ from Berkeley are much better than this model (and the code is open source as well). Furthermore, those better results have the advantage of a much simpler model. This model has a fairly complicated architecture (a complex residual concatenation setup) and many more parameters (I would guess anywhere between 2x-10x as many, but I'd have to take a closer look), w…
The authors of that point out that those are the especially successful cases. Presumably the the new article also showcases the success.
For comparability, I think it would be best if we could see outputs for the two models for the same, chosen in advance and not cherry picked, images.
Re: Show HN: Open source colorizing grayscale images with NN
#65Re: Show HN: Open source colorizing grayscale images with NN
#66These results: http://richzhang.github.io/colorization/ from Berkeley are much better than this model (and the code is open source as well). Furthermore, those better results have the advantage of a much simpler model. This model has a fairly complicated architecture (a complex residual concatenation setup) and many more parameters (I would guess anywhere between 2x-10x as many, but I'd have to take a closer look), w…
Idle thought: Could colorization be used to (lossy) compress full color images (usefully)?
What I imagine is full color input -> create B/W & color histogram (list of colors used) -> image viewer uses colorization algorithm to reapply colors.
Re: Show HN: Open source colorizing grayscale images with NN
#67Re: Show HN: Open source colorizing grayscale images with NN
#68These results: http://richzhang.github.io/colorization/ from Berkeley are much better than this model (and the code is open source as well). Furthermore, those better results have the advantage of a much simpler model. This model has a fairly complicated architecture (a complex residual concatenation setup) and many more parameters (I would guess anywhere between 2x-10x as many, but I'd have to take a closer look), w…
Idle thought: Could colorization be used to (lossy) compress full color images (usefully)? What I imagine is full color input -> create B/W & color histogram (list of colors used) -> image viewer uses colorization algorithm to reapply colors.
I don't really know a ton about image compression, but I exported the same photo to jpg using the same settings twice: once with 3 channels and once desaturated and then with two channels hidden (I couldn't figure out how to make a 1-channel jpg in gimp, no sure if it's possible). The 1-channel export had less than 30% file size reduction.
I don't think a compression technique that would require that much processing power and have that little size reduction would be too useful.
Re: Show HN: Open source colorizing grayscale images with NN
#69Earlier quoted context omitted.
I'd imagine that many people wouldn't even notice (unless the truck's color is part of the plot)
Maybe it's about a truck painting shop, and every time they paint something, it either doesn't change color, or get a color different from what the customer ordered. I would watch that.
You mean you would watch paint dry?
Re: Show HN: Open source colorizing grayscale images with NN
#70I'd apply it to an old B&W film to show off. Imagine Ben Hur or Citizen Kane in color!
I see a potential problem with moving pictures - the neural network might decide that while red was an appropriate color for the truck in the last frame, blue is more likely in this frame.
One idea here is to adopt a recent generative approach: a CNN which starts with two noise image inputs, and then repeatedly tweaks it plus a new noise image over multiple inputs until it does one last tweak to a final version. The noise serves as a RNG for making choices to the built-up image, I think. You could apply this recurrent idea to movies too: for the first BW frame, pass in a noise image and the BW frame, get out a C frame; now for the second BW frame, pass in the BW frame but also the C frame from before. The CNN may gradually learn to transfer colors from the C frame to the BW frame, thereby maintaining temporal coherency.
(Or you could just try to use a RNN directly and keep hidden state from frame to frame.)