Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization

Xiang Gao, Yuqi Zhang, Yingjie Tian
2022 International Conference on Machine Learning  
Image cartoonization is recently dominated by generative adversarial networks (GANs) from the perspective of unsupervised image-to-image translation, in which an inherent challenge is to precisely capture and sufficiently transfer characteristic cartoon styles (e.g., clear edges, smooth color shading, abstract fine structures, etc.). Existing advanced models try to enhance cartoonization effect by learning to promote edges adversarially, introducing style transfer loss, or learning to align
more » ... e from multiple representation space. This paper demonstrates that more distinct and vivid cartoonization effect could be easily achieved with only basic adversarial loss. Observing that cartoon style is more evident in cartoon-texturesalient local image regions, we build a regionlevel adversarial learning branch in parallel with the normal image-level one, which constrains adversarial learning on cartoon-texture-salient local patches for better perceiving and transferring cartoon texture features. To this end, a novel cartoontexture-saliency-sampler (CTSS) module is proposed to dynamically sample cartoon-texturesalient patches from training data. With extensive experiments, we demonstrate that texture saliency adaptive attention in adversarial learning, as a missing ingredient of related methods in image cartoonization, is of significant importance in facilitating and enhancing image cartoon stylization, especially for high-resolution input pictures.
dblp:conf/icml/GaoZT22 fatcat:bjr5qzjp6nfehdsyppu5ka5nly