標題: Adversarial Colorization Of Icons Based On Structure And Color Conditions
作者: Sun, Tsai-Ho
Lai, Chien-Hsun
Wong, Sai-Keung
Wang, Yu-Shuen
交大名義發表
National Chiao Tung University
關鍵字: Icon;colorization;generative adversarial networks
公開日期: 1-一月-2019
摘要: We present a system to help designers create icons that are widely used in banners, signboards, billboards, homepages, and mobile apps. Designers are tasked with drawing contours, whereas our system colorizes contours in different styles. This goal is achieved by training a dual conditional generative adversarial network (GAN) on our collected icon dataset. One condition requires the generated image and the drawn contour to possess a similar contour, while the other anticipates the image and the referenced icon to be similar in color style. Accordingly, the generator takes a contour image and a man-made icon image to colorize the contour, and then the discriminators determine whether the result fulfills the two conditions. The trained network is able to colorize icons demanded by designers and greatly reduces their workload. For the evaluation, we compared our dual conditional GAN to several state-of-the-art techniques. Experiment results demonstrate that our network is over the previous networks. Finally, we will provide the source code, icon dataset, and trained network for public use.
URI: http://dx.doi.org/10.1145/3343031.3351041
http://hdl.handle.net/11536/153831
ISBN: 978-1-4503-6889-6
DOI: 10.1145/3343031.3351041
期刊: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
起始頁: 683
結束頁: 691
顯示於類別:會議論文