What's the application and/or interest in colorizing images? Does it generalize to other types of problems?
Show HN: Open source colorizing grayscale images with NN
51–60 of 78 posts
Re: Show HN: Open source colorizing grayscale images with NN
#52Earlier quoted context omitted.
How would they know that the vehicles, say, were supposed to be the same colour. I'm thinking The Italian Job - the same model of cars are used and are distinguished by their colours. Also what about when different vehicles are painted by the production team to look the same (for stunts say), the computer could rightly recognise them as different vehicles - how would it then know that they're supposed to be the same.…
That TIJ cars were distinguishable only by color was made possible by filming in color. A BW movie would not make a film requiring distinguishing colors that filmed as equal shades of grey. In any case, any such colorizing system would be designed to accept a bit of guidance here and there from the artist. This is much like when an OCR'd document needs a bit of touch-up. And even if it wasn't perfect, many BW movies…
Even though already perfectly enjoyable, I'm thinking Kurosawa films like Seven Samurai and Yojimbo. Man that would be something.
Re: Show HN: Open source colorizing grayscale images with NN
#53The title says it's open source, but I couldn't actually see what the license is? (Maybe I missed it?)
And it looks like you have to download a torrent in order to get something. But yeah, it's missing a license and is still proprietary.
The torrent contains the parameters for another neural network, VGG16, that this network makes use of. VGG16 is a network developed by the Visual Geometry Group at Oxford[1]. They released their parameters under CC BY-NC 4.0 to save others from spending 2-3 weeks[2] training the network. Someone else converted those parameters to work with TensorFlow[3], which is what the torrent in this repository is.
I'm interested to see if neural network parameters become the new "binary blob". While in theory you could always retrain the network yourself, actually doing so takes a lot of work fiddling with the network's hyperparameters and requires significant computing resources.
[1] http://www.robots.ox.ac.uk/~vgg/research/very_deep/
[2] "On a system equipped with four NVIDIA Titan Black GPUs, training a single net took 2–3 weeks depending on the architecture." - arXiv:1409.1556
Re: Show HN: Open source colorizing grayscale images with NN
#54Earlier quoted context omitted.
I think it was a reference to this concept: http://bikeshed.com/
no, it was about this one: https://en.wikipedia.org/wiki/Bikeshed_color
How about we stop arguing about which link to use and just pick one? I propose http://amzn.com/0345282779. Of the three links proposed so far, this one is clearly the most authoritative.
Re: Show HN: Open source colorizing grayscale images with NN
#55I don't know if OP will see this but I'd love it if you could use your experience making this to write up a blog post about how it works or port it to being able to adjust color scales for color blind people.
I'd love to combine this technology with this: http://matplotlib.org/style_changes.html
You would probably have some cool results as you could generate examples of what they would look like to color blind people, and a corrected set so color blind people could see them.
Would be a cool, and I am assuming simpler problem then the one you have already managed to solve.
Good show, great work.
Re: Show HN: Open source colorizing grayscale images with NN
#56These 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…
And the thread concerning that much better model:
https://news.ycombinator.com/item?id=11403653
Re: Show HN: Open source colorizing grayscale images with NN
#57Can this be used to train a model which can un-blur an image?
Re: Show HN: Open source colorizing grayscale images with NN
#58Re: Show HN: Open source colorizing grayscale images with NN
#59I'm looking for a technique that can upscale images nicely (using NNs).
I've found this: [1], but the results seem somewhat disappointing. One of the problems is that the quality measures are (in my case) subjective (the results should look convincing but need not be "perfect", whatever that may mean).
[1] http://engineering.flipboard.com/2015/05/scaling-convnets/
Re: Show HN: Open source colorizing grayscale images with NN
#60Earlier quoted context omitted.
You're right, it would be a fun side effect to see the color change between different scenes :) I guess there's not enough in commercial interest in fixing these problems, but it can be probably done with the current algorithms. Precise 3D reconstruction is much more important than colour reconstruction.
Would it be possible to have some sort of semantic naming coupled to it 'the car in this scene is red', that could be fixed by humans, maybe even by talking to the NN? That's when this stuff starts getting fun IMO - human language together with superhuman domain knowledge.
Or even using the previously processed frames as reference the next time the shot appears