Unsupervised anime avatar sketch colorization based on reuse discriminators for encoding

Sicong Zhang; Jiting Zhou

doi:10.1117/12.2635688

6 May 2022 Unsupervised anime avatar sketch colorization based on reuse discriminators for encoding

Sicong Zhang, Jiting Zhou

Proceedings Volume 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022); 1225605 (2022) https://doi.org/10.1117/12.2635688
Event: 2022 International Conference on Electronic Information Engineering, Big Data and Computer Technology, 2022, Sanya, China

Abstract

Sketch or line art coloring is a research field with great market demand. Although the effect of some previous coloring methods is effective, it is easy to have the problem of color mixing in the facial area. In this method, based on our previous work, we use the latest image conversion framework NICE-GAN instead of CycleGAN to make the network framework more compact, and apply the multi-scale discriminator structure to make the conversion effect have more information and higher training efficiency. At the same time, combined with the attention mechanism module in the previous work, the model can learn the key coloring in the facial features area through the feature map, so as to reduce the surrounding color mixing. At the same time, due to the use of unsupervised network, the whole process is fast and automatic. It can be used for quick coloring of user-defined animation avatars. It is very friendly to novice users who can't color. The final experiment also proves that this method has better effect in facial region than other previous line drawing coloring methods, significantly reduces color mixing, and has higher training efficiency.

Citation Download Citation

Sicong Zhang and Jiting Zhou "Unsupervised anime avatar sketch colorization based on reuse discriminators for encoding", Proc. SPIE 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022), 1225605 (6 May 2022); https://doi.org/10.1117/12.2635688

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Computer programming

Gallium nitride

Solid modeling

Dysprosium

Image quality

Performance modeling

Content addressable memory

Show All Keywords

Keywords/Phrases

Search In:

Publication Years