A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed renders. To address this, we resort to 3D Gaussian Splatting (3DGS), which has recently been shown to produce realistic free-viewpoint avatars. Given a multiview sequence, we extract a FLAME mesh, solve a curvature-weighted Poisson equation, and obtain its exaggerated form. However, directly deforming the Gaussians yields poor results, necessitating the synthesis of pseudo-ground-truth caricature images by warping each frame to its exaggerated 2D representation using local affine transformations. We then devise a training scheme that alternates real and synthesized supervision, enabling a single Gaussian collection to represent both natural and exaggerated avatars. This scheme improves fidelity, supports local edits, and allows continuous control over the intensity of the caricature. In order to achieve real-time deformations, an efficient interpolation between the original and exaggerated surfaces is introduced. We further analyze and show that it has a bounded deviation from closed-form solutions. In both quantitative and qualitative evaluations, our results outperform prior work, delivering photorealistic, geometry-controlled caricature avatars.

翻译：本文提出了一种兼具照片级真实感与可控性的三维人脸漫画化框架。我们首先采用基于本征高斯曲率的曲面夸张技术，但发现结合纹理后易产生过度平滑的渲染结果。为解决此问题，我们转向近期被证明能生成逼真自由视角虚拟形象的3D高斯泼溅（3DGS）技术。给定多视角序列，我们提取FLAME网格，求解曲率加权泊松方程，获得其夸张化形态。然而直接对高斯分布进行变形会导致效果不佳，因此我们通过局部仿射变换将每帧图像扭曲至其对应的夸张化二维表征，合成了伪真实漫画图像。随后设计了一种交替使用真实数据与合成数据监督的训练方案，使单一高斯集合能够同时表征自然状态与夸张化的虚拟形象。该方案提升了保真度，支持局部编辑，并允许对漫画化强度进行连续控制。为实现实时变形，我们引入了原始曲面与夸张曲面之间的高效插值方法，并通过分析证明该方法与闭式解存在有界偏差。在定量与定性评估中，我们的方法均优于现有工作，能够生成具有照片级真实感且几何可控的漫画虚拟形象。