Colorful Image Colorization

Code

• github.com/richzhang/colorization
  Officialcaffe2★ 0
• github.com/amogh7joshi/media-vision
  pytorch★ 2
• github.com/Sunkua/Colorizer
  pytorch★ 0
• github.com/yangyucheng000/Colorization-
  mindspore★ 0
• github.com/marumse/colorize_images
  none★ 0
• github.com/prathyusha995912/prathyusha
  caffe2★ 0
• github.com/ryanwng12/img-colorization
  pytorch★ 0
• github.com/BerenLuthien/HyperColumns_ImageColorization
  tf★ 0
• github.com/bluejurand/Photos-colorization
  tf★ 0
• github.com/fer-moreira/ColorizerBot
  none★ 0

Abstract

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

Tasks

Reproductions