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

Colorizing black and white photos with deep learning

blog.floydhub.com

Post reply on HN
Print view View original

11–20 of 52 posts

Re: Colorizing black and white photos with deep learning

#11

Post by mholmes680 »

saip wrote: post #9
flsantos wrote: post #5

Interesting! If nowadays, pictures are colorized by hand in photoshop, it wouldn't be practical to colorize a full black and white movie. I guess this deep learning approach would solve this problem and colorize old black and white classic movies.

Agreed. I imagine this has applications in compression as well. You could stream a movie (or a football game) in black and white and enable each device to color it on the spot. A similar technique could also be done for HD/3D/VR.

that is an amazing idea.

Re: Colorizing black and white photos with deep learning

#13

Post by houqp »

ReDeiPirati wrote: post #12

It could be really interesting if it could return different coloured versions and provide a way to explore this different style.

What's even cooler is adding support for human annotations so users can selectively give colorization hints for different parts of the image to customize the output.

Re: Colorizing black and white photos with deep learning

#15

Post by saip »

ReDeiPirati wrote: post #12

It could be really interesting if it could return different coloured versions and provide a way to explore this different style.

A GAN style approach to learning and generating variants could be interesting as well. It could generate a couple of hundred plausible versions. Then you have another network that is trained to differentiate between fake and real colored photos which picks the best version.

Re: Colorizing black and white photos with deep learning

#18

Post by zardo »

iluvmylife wrote: post #2

The averaging problem in colorization is interesting. If it learns that an apple can be red, green and even yellow - how does it know how to color it? A HN user in an earlier thread suggested to use a fake/real colorization classifiers as a loss function. [1] But I still feel that it would not solve the averaging problem. It would hop between different colors and probably converge to brown. I haven’t come across a pl…

>But I still feel that it would not solve the averaging problem. It would hop between different colors and probably converge to brown.

At least to the extent that GANs work, it works. They will alternate between the observed colours based on the noise vector. They do not simply converge to averages, because the discriminator easily recognizes brown apples as fakes.

Re: Colorizing black and white photos with deep learning

#19

Post by taneq »

iluvmylife wrote: post #2

The averaging problem in colorization is interesting. If it learns that an apple can be red, green and even yellow - how does it know how to color it? A HN user in an earlier thread suggested to use a fake/real colorization classifiers as a loss function. [1] But I still feel that it would not solve the averaging problem. It would hop between different colors and probably converge to brown. I haven’t come across a pl…

> If it learns that an apple can be red, green and even yellow - how does it know how to color it?

I dunno, does it look more like a red apple, a green apple or a yellow apple?

Re: Colorizing black and white photos with deep learning

#20

Post by zardo »

saip wrote: post #9
flsantos wrote: post #5

Interesting! If nowadays, pictures are colorized by hand in photoshop, it wouldn't be practical to colorize a full black and white movie. I guess this deep learning approach would solve this problem and colorize old black and white classic movies.

Agreed. I imagine this has applications in compression as well. You could stream a movie (or a football game) in black and white and enable each device to color it on the spot. A similar technique could also be done for HD/3D/VR.

Yes, you provide a handful of full data keyframes and reconstruct the details of the stream from the middle out.
Post reply on HN