论文标题
汽车：面部动画片的自动几何扭曲
AutoToon: Automatic Geometric Warping for Face Cartoon Generation
论文作者
论文摘要
漫画是一种夸张的艺术肖像，它扩大了人类面孔的独特而细致的特征。这项任务通常留给艺术家，因为事实证明，使用自动化方法很难很好地捕获受试者的独特特征。深度端到端方法的最新发展在捕捉风格和更高层次的夸张方面取得了令人鼓舞的结果。但是，面部扭曲的漫画的关键部分对于这些系统仍然具有挑战性。在这项工作中，我们提出了Autotoon，这是第一种监督的深度学习方法，该方法为漫画的翘曲部分产生高质量的翘曲。它与样式完全脱离，可以与任何风格化方法配对，以创建各种漫画。与先前的艺术相反，我们利用了senet和空间变压器模块，直接在艺术家扭曲场上进行训练，并在翘曲之前和之后施加损失。如我们的用户研究所示，我们实现了吸引人的夸张，从而放大了面部的区别特征，同时保存面部细节。
Caricature, a type of exaggerated artistic portrait, amplifies the distinctive, yet nuanced traits of human faces. This task is typically left to artists, as it has proven difficult to capture subjects' unique characteristics well using automated methods. Recent development of deep end-to-end methods has achieved promising results in capturing style and higher-level exaggerations. However, a key part of caricatures, face warping, has remained challenging for these systems. In this work, we propose AutoToon, the first supervised deep learning method that yields high-quality warps for the warping component of caricatures. Completely disentangled from style, it can be paired with any stylization method to create diverse caricatures. In contrast to prior art, we leverage an SENet and spatial transformer module and train directly on artist warping fields, applying losses both prior to and after warping. As shown by our user studies, we achieve appealing exaggerations that amplify distinguishing features of the face while preserving facial detail.
