Colorful Image Colorization
Richard Zhang, Phillip Isola, Alexei A. Efros, 2016
Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible colour version of the photograph.This problem is clearly under constrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorisation. We propose a fully automatic approach that produces vibrant and realistic colorisation. 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 colours 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 colour images.