We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color distributions, we train our model to predict per-pixel color histograms. This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation. On both fully and partially automatic colorization tasks, we outperform existing methods. We also explore colorization as a vehicle for self-supervised visual representation learning.
@article{arxiv.1603.06668,
title = {Learning Representations for Automatic Colorization},
author = {Gustav Larsson and Michael Maire and Gregory Shakhnarovich},
journal= {arXiv preprint arXiv:1603.06668},
year = {2017}
}