Learning Representations for Automatic Colorization

Gustav Larsson, Michael Maire, Gregory Shakhnarovich
3/22/2016
cs.CV

Official code: gustavla/autocolorize (220 stars, BSD-3-Clause, last commit 2017-09-05).

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.

View on arXivView PDF

Code Implementations(1)

gustavla/autocolorizeOfficial100%
BSD-3-Clause

Automatic colorizaton of grayscale images using Deep Learning

22063C++, CudaApr 3, 20169 years agoBSD-3-Clause

Similar Papers

Real-Time User-Guided Image Colorization with Learned Deep Priors

90% match1 repo2.7k2017

MMC: Multi-Modal Colorization of Images using Textual Descriptions

89% match2023

Image Colorization with Generative Adversarial Networks

88% match1 repo2692018

Diffusing Colors: Image Colorization with Text Guided Diffusion

87% match2023

ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution

87% match1 repo2082019

SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization

87% match2023

Cite this paper

@article{larsson2016learning,
  title  = {Learning Representations for Automatic Colorization},
  author = {Gustav Larsson and Michael Maire and Gregory Shakhnarovich},
  year   = {2016},
  eprint = {1603.06668},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1603.06668}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1603.06668.svg)](https://codeofpaper.com/paper/1603.06668)

Discussion