Colorizing and restoring old images with deep learning
1–10 of 107 posts
Re: Colorizing and restoring old images with deep learning
#2The most interesting exhibit for me is "People watching a television set for the first time", where everything is colorized except the TV image, which correctly remains B&W. I wonder what kind of a training set provided the neural network with this notion.
Re: Colorizing and restoring old images with deep learning
#3I've to admit I have no clue about machine learning, but what I notice is that this seems to have preferred colors for things that can actually have many different colors, most notably clothes. They're almost always this blueish slightly purple color here, even the samurai. Don't get me wrong, this is still awesome and I might try this on some old photos from my grandparents. I'm just wondering if and how one can prevent these things from picking this one ideal color for something and instead have it randomize a bit, since obviously you can't really know what color some jacket really was. (except maybe if the picture is a black and white photo of a PAL TV program.)
Re: Colorizing and restoring old images with deep learning
#4Is it just me or do the example images seem overly biased toward coloring clothing as blue?
Re: Colorizing and restoring old images with deep learning
#5>> BEEFY Graphics card. I'd really like to have more memory than the 11 GB in my GeForce 1080TI (11GB). You'll have a tough time with less. The Unet and Critic are ridiculously large but honestly I just kept getting better results the bigger I made them.
Wow!
Re: Colorizing and restoring old images with deep learning
#6This seems almost too good to be true. One thing I find very striking is how it gets skin tones very plausible across people of different ethnicities (though the majority of subjects in the picture appear of european descent).
Unless a) my brain is applying more interpretation to these pictures than I realize or b) the author (intentionally or not) picked out pictures that show the best results
Re: Colorizing and restoring old images with deep learning
#7Anyone else left wondering if the hand really was red in the photo?
Re: Colorizing and restoring old images with deep learning
#8I've to admit I have no clue about machine learning, but what I notice is that this seems to have preferred colors for things that can actually have many different colors, most notably clothes. They're almost always this blueish slightly purple color here, even the samurai. Don't get me wrong, this is still awesome and I might try this on some old photos from my grandparents. I'm just wondering if and how one can pre…
The Seneca Native in 1908 example seems the most absurd to me. I know the software has no notion of a "fabric" or "clothing" but it's very rare for brown or beige things to fade to blue (or vise versa). In real life things when transition from brown/beige to another color that other color tends to be a red orange or yellow. I know from the known issue that it likes blue but it still seems very odd that it chose to fade from brown to blue like that.
Re: Colorizing and restoring old images with deep learning
#9I've to admit I have no clue about machine learning, but what I notice is that this seems to have preferred colors for things that can actually have many different colors, most notably clothes. They're almost always this blueish slightly purple color here, even the samurai. Don't get me wrong, this is still awesome and I might try this on some old photos from my grandparents. I'm just wondering if and how one can pre…
This is mentioned in "known issues" and near "Generator Loss"
Re: Colorizing and restoring old images with deep learning
#10>> BEEFY Graphics card. I'd really like to have more memory than the 11 GB in my GeForce 1080TI (11GB). You'll have a tough time with less. The Unet and Critic are ridiculously large but honestly I just kept getting better results the bigger I made them. Wow!
This basically sounds like "the more I let the machine memorize, the better it did." Not necessarily bad, mind you, just amusing.