3D- CariGAN：一种从人脸照片生成3D漫画的端到端解决方案
3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos
摘要：
漫画是一种在娱乐界备受关注的人脸艺术风格。到目前为止，存在一些3D漫画生成方法，并且所有这些方法都需要一些漫画信息（例如，漫画草图或2D漫画）作为输入。然而，这种输入很难由非专业用户提供。在本文中，我们提出了一个端到端的深度神经网络模型，可以直接从正常的2D人脸照片生成高质量的3D漫画。对于我们的系统来说，最具挑战性的问题是人脸照片的源域（以正常的2D人脸为特征）与3D漫画的目标域（以3D夸张的人脸形状和纹理为特征）显著不同。为了解决这个问题，我们：（1）建立一个包含5，343个3D漫画网格的大数据集，并使用它在3D漫画形状空间中建立PCA模型;（2）从输入的人脸照片重建一个正常的完整3D头部，并使用其在3D漫画形状空间中的PCA表示来建立输入照片和3D漫画形状之间的对应关系;（3）在前人关于漫画心理学研究的基础上，提出了一种新的人物失落和漫画失落。实验结果表明，该系统可以直接从正常人脸照片生成高质量的三维漫画。
英文摘要：
Caricature is a type of artistic style of human faces that attracts considerable attention in the entertainment industry. So far a few 3D caricature generation methods exist and all of them require some caricature information (e.g., a caricature sketch or 2D caricature) as input. This kind of input, however, is difficult to provide by non-professional users. In this paper, we propose an end-to-end deep neural network model that generates high-quality 3D caricatures directly from a normal 2D face photo. The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures). To address this challenge, we: (1) build a large dataset of 5,343 3D caricature meshes and use it to establish a PCA model in the 3D caricature shape space; (2) reconstruct a normal full 3D head from the input face photo and use its PCA representation in the 3D caricature shape space to establish correspondences between the input photo and 3D caricature shape; and (3) propose a novel character loss and a novel caricature loss based on previous psychological studies on caricatures. Experiments including a novel two-level user study show that our system can generate high-quality 3D caricatures directly from normal face photos.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
