English

Learning Representations for Automatic Colorization

Computer Vision and Pattern Recognition 2017-08-15 v3

Abstract

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.

Keywords

Cite

@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}
}

Comments

ECCV 2016 (Project page: http://people.cs.uchicago.edu/~larsson/colorization/)