News for hackers. Stuff that matters.
Re:Colorizing and restoring old images with deep learning by dsfyu404ed on Friday November 02, 2018 @12:24PM (#18364290)
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 by samstave on Saturday November 03, 2018 @05:11PM (#18372509)
Take a look at the two most famous indian textiles from the 1800s which sold For millions/appraised for millions.

They were chiefs blankets.

They were blue/had no red

https://www.youtube.com/watch?v=9cGlS05233Q

https://www.youtube.com/watch?v=WJw2qCnhea0

Re:Colorizing and restoring old images with deep learning by onemoresoop on Friday November 02, 2018 @02:18PM (#18365358)
To me the Seneca native's skin on the hand seems a bit to reddish. I find these photos to have very high saturation. I think this could be adjusted and get subtler effects. It's still amazing that this is possible with no human intervention but at the same time, from a different perspective, I find that the originals have their own charm that I would leave it like that.
Re:Colorizing and restoring old images with deep learning by draugadrotten on Friday November 02, 2018 @05:36PM (#18366970)
Is it unthinkable that the seneca girl actually had her hand painted red, for decoration or as a symbol of something? Perhaps her father/brother etc was a fighter and this was a way to keep spirits up while he was in the war?
Re:Colorizing and restoring old images with deep learning by blackflame7000 on Friday November 02, 2018 @05:49PM (#18367042)
If you compare the tone of her hand to her face in the black and white image you can clearly see that the colors are different.