Hey everybody! So a few weeks ago, I got inspired by the odd effect of Jeremy’s super-resolution demo where it corrected the colour balance of an image and decided to see if I could create a neural net architecture to recolour some old BBC shows where the original recording has been lost, but it still exists in a b/w format. Early days, but my initial experiments seem positive:
(at the moment, I’ve ended up with a partial U-Net architecture)
Now that my shiny 1080Ti has arrived, I’ll be gearing up for a run on the full dataset probably by the end of the month, and I’ll stick up the full code after I’ve cleaned it up some ;).
Creative project. Good write up. Happy to see you had some success.
Nicely done. I look forward to more.
Thanks for posting! This is some really, really cool stuff. Will be looking forward to following your progress.
Thanks, all! @pietz - I had actually been wondering this week whether it might also be a good fit for getting to grips with WGANs, so thanks for posting that!
Ryan Dahl also has a great write up on some of his work on colorization:
Also somewhat related, I’ve spent some time on subpixel convolution, and have found it to be quite fast for upsampling.