Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Open source colorizing grayscale images with NN

github.com

Post reply on HN
Print view View original

41–50 of 78 posts

Re: Show HN: Open source colorizing grayscale images with NN

#41

Post by nothrabannosir »

lucideer wrote: post #34
syockit wrote: post #27

Earlier quoted context omitted.

It is open source. You can see the source. The license is no-license, so you can (only) fork it. That way, people can clone from your username instead of the original author, although that doesn't make any difference as they're all hosted on GitHub.

You seem to be getting downvotes because you don't understand what the term "open source" means, but nobody has offered to explain so: Open source does not just mean you can see the source. From Wikipedia[0]: "Open-source software is computer software with its source code made available with a license in which the copyright holder provides the rights to study, change, and distribute the software to anyone and for any…

Not OP, but---I've been in software and OSS for a long time now, and I never knew this. I thought the term for that was Free Software.

In fact, looking closely at that definition, isn't practically nothing open source?

"Open-source software is computer software with its source code made available with a license in which the copyright holder provides the rights to study, change, and distribute the software to anyone and for any purpose."

I.e. public domain? Any other license lives precisely to limit those rights of distribution, no?

Anyway, just pedantry. I see your point. Learn something new every day.

Re: Show HN: Open source colorizing grayscale images with NN

#42

Post by argonaut »

These 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), which means it's much slower to run and takes up more memory (disk and RAM).

I'd also say that in general the better model does things that are a lot more common sense: using the CIE Lab color space (perceptually uniform), omitting pooling, using a classification loss instead of regression (regression in generally performs poorly in deep learning), etc.

Re: Show HN: Open source colorizing grayscale images with NN

#43

Post by omtose »

pbhjpbhj wrote: post #35
WalterBright wrote: post #30

Earlier quoted context omitted.

I suspect that if an artist selected colors for a few key frames, the computer could figure out the rest of the frames.

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.…

>the same model of cars are used and are distinguished by their colours

Aren't we talking about a B&W film? In that case the colour (or its lack of) wouldn't communicate any information.

Re: Show HN: Open source colorizing grayscale images with NN

#44

Post by WalterBright »

pbhjpbhj wrote: post #35
WalterBright wrote: post #30

Earlier quoted context omitted.

I suspect that if an artist selected colors for a few key frames, the computer could figure out the rest of the frames.

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 would be made much more watchable, like the 1927 Wings, which is crying out to be colorized (and have a soundtrack added).

Re: Show HN: Open source colorizing grayscale images with NN

#45

Post by lucideer »

nothrabannosir wrote: post #41
lucideer wrote: post #34

Earlier quoted context omitted.

You seem to be getting downvotes because you don't understand what the term "open source" means, but nobody has offered to explain so: Open source does not just mean you can see the source. From Wikipedia[0]: "Open-source software is computer software with its source code made available with a license in which the copyright holder provides the rights to study, change, and distribute the software to anyone and for any…

Not OP, but---I've been in software and OSS for a long time now, and I never knew this. I thought the term for that was Free Software. In fact, looking closely at that definition, isn't practically nothing open source? "Open-source software is computer software with its source code made available with a license in which the copyright holder provides the rights to study, change, and distribute the software to anyone a…

I think you've highlighted an inaccuracy, or at least a lack of clarity, in the Wikipedia article. I guess a Wikipedian could argue it should be interpreted as "for any purpose depending on the chosen licence", but that's definitely not clear.

Re: Open source vs Free software, this is a matter for debate (the tendency being too associate Free software with the more copyleft/viral/gnu-ish side of things), but I would definitely say that both involve explicit licencing, as opposed to potentially implicit " all rights reserved " style regional copyright.

Re: Show HN: Open source colorizing grayscale images with NN

#46

Post by WalterBright »

pbhjpbhj wrote: post #35
WalterBright wrote: post #30

Earlier quoted context omitted.

I suspect that if an artist selected colors for a few key frames, the computer could figure out the rest of the frames.

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.…

BW filmmakers were, of course, well aware that they were filming in BW and would select colors for sets and costumes that would look good in BW. For example, chocolate milk was used for blood. You wouldn't want a colorizer to determine the actual colors, but the intended colors!

Even today, directors rarely seem to want to film in actual color. They'll tint everything sepia, or that hideous blue-orange scheme that is so popular these days.

http://priceonomics.com/why-every-movie-looks-sort-of-orange...

Re: Show HN: Open source colorizing grayscale images with NN

#47

Post by pionar »

xiphias wrote: post #19
thomasahle wrote: post #16

Earlier quoted context omitted.

There might be a few scenes in between the viewings of the truck.

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.

>it would be a fun side effect to see the color change between different scenes :)

Now that's a horse of a different color[0]!

[0] http://oz.wikia.com/wiki/Horse_of_a_Different_Color

Re: Show HN: Open source colorizing grayscale images with NN

#48

Post by rimantas »

fmeyer wrote: post #23

I'm colorblind and I can't tell the difference between the prediction and the GT. My coworker says that they have slight differences in some colors. Congrats, you wrote the first colorblind NN ever!

I'd say the differences are very well expressed.

Re: Show HN: Open source colorizing grayscale images with NN

#49

Post by gcr »

g_sch wrote: post #22

I'd be interested to see what kind of hidden biases this might reveal, especially about people, e.g. skin tone, eye color, etc.

Agreed. I wonder how good this model is at filling the skin tone of someone. It would be sad if (for example) it turned everybody into white people or something like that.

In biometrics, there's been similar cases of software like face detectors and face recognition working very well on people from China and not very well for other people, because all the researchers who trained those models only had available large public databases from Chinese universities. The model hadn't seen any other ethnicity so its performance on "non-Chinese" folks wasn't surprising.

Re: Show HN: Open source colorizing grayscale images with NN

#50

Post by m_mueller »

xiphias wrote: post #19
thomasahle wrote: post #16

Earlier quoted context omitted.

There might be a few scenes in between the viewings of the truck.

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.
Post reply on HN