An effective anime character generation method using DCGAN

Yunqi Du; Yuan Gao; Linxuan Nie; Xingdong Xu

doi:10.1117/12.2641189

19 October 2022 An effective anime character generation method using DCGAN

Yunqi Du, Yuan Gao, Linxuan Nie, Xingdong Xu

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122945H (2022) https://doi.org/10.1117/12.2641189
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

Face generation of anime characters, this fairy belongs to the category of image generation, given a specific anime character. We use generative models to further refine the picture. In addition, we do our best to require our projects to be the most authentic and detailed restoration of the original characteristics of the cartoon characters. For online animation face generation, first we apply a large amount of datasets and materials from DCGAN offline mobile phones and obtain an offline training model, so we can model the overall facial features. During the online process, input a specified cartoon character and fine-tune their characteristics to adapt to the data of different faces. Consequently, we compared offline and online generated data, and obtained the effectiveness of our magic through the results.

Citation Download Citation

Yunqi Du, Yuan Gao, Linxuan Nie, and Xingdong Xu "An effective anime character generation method using DCGAN", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122945H (19 October 2022); https://doi.org/10.1117/12.2641189

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available