Infrared Image Colorization Based on a Triplet DCGAN Architecture
Abstract
This paper proposes a novel approach for colorizing near infrared (NIR) images using a Deep Convolutional Generative Adversarial Network (GAN) architecture. The proposed approach is based on the usage of a triplet model for learning each color channel independently, in a more homogeneous way. It allows a fast convergence during the training, obtaining a greater similarity between the colored NIR image and the corresponding ground truth. The proposed approach has been evaluated with a large data set of NIR images and compared with a recent approach, which is also based on a GAN architecture where all the color channels are obtained at the same time.
Cite
Text
Suarez et al. "Infrared Image Colorization Based on a Triplet DCGAN Architecture." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.32Markdown
[Suarez et al. "Infrared Image Colorization Based on a Triplet DCGAN Architecture." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/suarez2017cvprw-infrared/) doi:10.1109/CVPRW.2017.32BibTeX
@inproceedings{suarez2017cvprw-infrared,
title = {{Infrared Image Colorization Based on a Triplet DCGAN Architecture}},
author = {Suarez, Patricia L. and Sappa, Angel Domingo and Vintimilla, Boris Xavier},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {212-217},
doi = {10.1109/CVPRW.2017.32},
url = {https://mlanthology.org/cvprw/2017/suarez2017cvprw-infrared/}
}