Li, SiminWen, QiangZhao, ShuangSun, ZixunHe, ShengfengEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lue2020-10-292020-10-2920201467-8659https://doi.org/10.1111/cgf.14170https://diglib.eg.org:443/handle/10.1111/cgf14170Cartoon is highly abstracted with clear edges, which makes it unique from the other art forms. In this paper, we focus on the essential cartoon factors of abstraction and edges, aiming to cartoonize real-world photographs like an artist. To this end, we propose a two-stage network, each stage explicitly targets at producing abstracted shading and crisp edges respectively. In the first abstraction stage, we propose a novel unsupervised bilateral flattening loss, which allows generating high-quality smoothing results in a label-free manner. Together with two other semantic-aware losses, the abstraction stage imposes different forms of regularization for creating cartoon-like flattened images. In the second stage we draw lines on the structural edges of the flattened cartoon with the fully supervised line drawing objective and unsupervised edge augmenting loss. We collect a cartoon-line dataset with line tracing, and it serves as the starting point for preparing abstraction and line drawing data. We have evaluated the proposed method on a large number of photographs, by converting them to three different cartoon styles. Our method substantially outperforms state-of-the-art methods in terms of visual quality quantitatively and qualitatively.Computing methodologiesNeural networksImage processing10.1111/cgf.14170587-599