Deep texture cartoonization via unsupervised appearance regularization. (June 2021)

• Record Type: Journal Article
• Authors: Wu, Huisi; Li, Yifan; Liu, Xueting; Li, Chengze; Wu, Wenliang
• Is Part Of: Computers & graphics. Volume 97(2021)
• Page Start: 99
• Page End: 107
• Publication Date: 2021-06
• Subjects: Texture Cartoonization -- Texture Appearance Regularization -- Unsupervised Learning -- Adversarial Learning; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2021.04.015
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: The first deep learning framework for texture cartoonization. A deep regularization module to predict and enhance the regularity of texture. An unsupervised module for texture cartoonization. Tailored self-supervised and adversarial objectives for network training. Graphical abstract: Abstract: Texture plays an important role in cartoon images to represent materials of objects and enrich visual attractiveness. However, manually crafting a cartoon texture is not easy, so amateurs usually directly use cartoon textures downloaded from the Internet. Unfortunately, Internet resources are quite limited and often patented, which restrict the users from generating visually pleasant and personalized cartoon textures. In this paper, we propose a deep learning based method to generate cartoon textures from natural textures. Different from the existing photo cartoonization methods that only aim to generate cartoonic images, the key to our method is to generate cartoon textures that are both cartoonic and regular. To achieve this goal, we propose a regularization module to generate a regular natural texture with similar appearance as the input, and a cartoonization module to cartoffonize the regularized natural texture into a regular cartoon texture. Our method successfully produces cartoonic and regular textures from various natural textures.