Towards Image Colorization with Random Forests

Helge Mohn, Mark Gaebelein, Ronny Hänsch, Olaf Hellwich

2018

Abstract

Image colorization refers to the task of assigning color values to grayscale images. While previous work is based on either user input or very large training data sets, the proposed method is fully automatic and based on several orders of magnitude less training data. A Random Forest variation is tailored towards the regression task of estimating the proper color values when presented with a grayscale image patch. A simple position prior as well as scale invariance are included in order to improve the estimation results. The proposed approach leads to satisfying results over various colorization tasks and compares favorably with state of the art based on convolutional networks.

Download


Paper Citation


in Harvard Style

Mohn H., Gaebelein M., Hänsch R. and Hellwich O. (2018). Towards Image Colorization with Random Forests. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 270-278. DOI: 10.5220/0006570002700278


in Bibtex Style

@conference{visapp18,
author={Helge Mohn and Mark Gaebelein and Ronny Hänsch and Olaf Hellwich},
title={Towards Image Colorization with Random Forests},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP},
year={2018},
pages={270-278},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006570002700278},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP
TI - Towards Image Colorization with Random Forests
SN - 978-989-758-290-5
AU - Mohn H.
AU - Gaebelein M.
AU - Hänsch R.
AU - Hellwich O.
PY - 2018
SP - 270
EP - 278
DO - 10.5220/0006570002700278
PB - SciTePress