Infrared Image Colorization Based on a Triplet DCGAN Architecture

Patricia L. Suarez, Angel D. Sappa, Boris X. Vintimilla; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 18-23

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Suarez_2017_CVPR_Workshops,
author = {Suarez, Patricia L. and Sappa, Angel D. and Vintimilla, Boris X.},
title = {Infrared Image Colorization Based on a Triplet DCGAN Architecture},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}