Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not yet been shown possible. Can we train a 3D GAN on such artistic data, while maintaining multi-view consistency and texture quality? To this end, we propose an adaptation framework, where the source domain is a pre-trained 3D-GAN, while the target domain is a 2D-GAN trained on artistic datasets. We then distill the knowledge from a 2D generator to the source 3D generator. To do that, we first propose an optimization-based method to align the distributions of camera parameters across domains. Second, we propose regularizations necessary to learn high-quality texture, while avoiding degenerate geometric solutions, such as flat shapes. Third, we show a deformation-based technique for modeling exaggerated geometry of artistic domains, enabling -- as a byproduct -- personalized geometric editing. Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains. Our contributions -- for the first time -- allow for the generation, editing, and animation of personalized artistic 3D avatars on artistic datasets.

翻译：现代3D-GAN通过在具有一致结构的大规模数据集上训练来合成几何与纹理。然而，在风格化艺术数据（通常包含未知且高度可变的几何结构与相机信息）上训练此类模型尚未被证明可行。我们能否在保持多视图一致性与纹理质量的同时，在艺术数据上训练3D-GAN？为此，我们提出一个自适应框架：源域为预训练的3D-GAN，目标域为在艺术数据集上训练的2D-GAN。随后将2D生成器的知识蒸馏到源域3D生成器中。具体而言，我们首先提出一种基于优化的方法，对齐跨域的相机参数分布；其次，引入必要的正则化项以学习高质量纹理，同时避免退化几何解（如扁平形状）；第三，展示一种基于形变的技术，用于建模艺术域的夸张几何，并作为副产品实现个性化几何编辑；最后，提出一种新颖的3D-GAN反演方法，连接源域与目标域的潜在空间。我们的贡献首次实现在艺术数据集上生成、编辑与动画化个性化的艺术风格3D化身。