Unsupervised Diverse Colorization via Generative Adversarial Networks
Abstract
Colorization of grayscale images is a hot topic in computer vision. Previous research mainly focuses on producing a color image to recover the original one in a supervised learning fashion. However, since many colors share the same gray value, an input grayscale image could be diversely colorized while maintaining its reality. In this paper, we design a novel solution for unsupervised diverse colorization. Specifically, we leverage conditional generative adversarial networks to model the distribution of real-world item colors, in which we develop a fully convolutional generator with multi-layer noise to enhance diversity, with multi-layer condition concatenation to maintain reality, and with stride 1 to keep spatial information. With such a novel network architecture, the model yields highly competitive performance on the open LSUN bedroom dataset. The Turing test on 80 humans further indicates our generated color schemes are highly convincible.
Cite
Text
Cao et al. "Unsupervised Diverse Colorization via Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017. doi:10.1007/978-3-319-71249-9_10Markdown
[Cao et al. "Unsupervised Diverse Colorization via Generative Adversarial Networks." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2017.](https://mlanthology.org/ecmlpkdd/2017/cao2017ecmlpkdd-unsupervised/) doi:10.1007/978-3-319-71249-9_10BibTeX
@inproceedings{cao2017ecmlpkdd-unsupervised,
title = {{Unsupervised Diverse Colorization via Generative Adversarial Networks}},
author = {Cao, Yun and Zhou, Zhiming and Zhang, Weinan and Yu, Yong},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2017},
pages = {151-166},
doi = {10.1007/978-3-319-71249-9_10},
url = {https://mlanthology.org/ecmlpkdd/2017/cao2017ecmlpkdd-unsupervised/}
}