Given a grayscale photograph as input, this paper attacks the problem of hallucinating a {\em 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 explore using class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward operation 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 subjects to choose between a generated and ground truth color image. Our method successfully fools humans 20\% of the time, significantly higher than previous methods.
View on arXiv