Tile Art Image Generation Using Conditional Generative Adversarial Networks
Tile Art Image Generation Using Conditional Generative Adversarial Networks
复制标题
DOI：
10.1109/candarw.2018.00047
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Naoki Matsumura;Hiroki Tokura;Yuki Kuroda;Yasuaki Ito;K. Nakano
中科院分区：
文献类型：
--
作者：
Naoki Matsumura;Hiroki Tokura;Yuki Kuroda;Yasuaki Ito;K. Nakano
图像到图像的转换是将一个域中的图像映射到另一个域中的相应图像的任务。这项任务包括各种类型的问题，如超分辨率、着色和艺术风格转移。近年来，随着深度学习的出现，该技术得到了迅速发展。本文的主要目的是提出一种基于条件生成对抗网络的机器学习方法的瓷砖艺术图像生成方法。为了制作瓷砖艺术图像的训练数据集，我们采用了一种基于贪心方法的正方形点阵图像生成方法。经过训练，该网络可以生成具有瓷砖结构的瓷砖艺术图像，并能很好地再现原始图像。在生成时间方面，贪心方法生成尺寸为4096x3072的瓷砖图像需要1322秒，而提出的机器学习方法需要0.593秒。
Image-to-image translation is a task of mapping an image in one domain to a corresponding image in another domain. The task includes various types of problems such as super-resolution, colorization, and artistic style transfer. In recent years, with the advent of deep learning, the technology has been rapidly advanced. The main purpose of this paper is to propose a tile art image generation method using machine learning approach based on conditional generative adversarial networks. To make the training data set of tile art images, we adopted a square-pointillism image generation method using the greedy approach. After training, the proposed network can generate tile art images that have the structure of tiles and reproduce the original images well. As regards generating time, the greedy approach takes 1322 seconds to generate tile art image of size 4096x3072, while the proposed machine learning approach takes 0.593 seconds.