CaricatureGS：利用高斯曲率誇張化3D高斯潑濺人臉

摘要

本文提出了一種具備照片級真實感且可控制的面部三維漫畫化框架。我們首先採用基於內在高斯曲率的表面誇張技術，該技術在結合紋理時容易產生過度平滑的渲染效果。為解決此問題，我們引入三維高斯潑濺技術（3DGS），該技術近期已被證實能生成逼真的自由視點虛擬形象。針對多視角序列，我們先提取FLAME網格，求解曲率加權泊松方程，獲得其誇張化形態。然而直接對高斯分佈進行變形會導致效果不佳，因此需通過局部仿射變換將每幀圖像扭曲至其誇張化的二維表徵，從而合成偽真實標註漫畫圖像。我們隨後設計了交替使用真實數據與合成數據監督的訓練方案，使單個高斯集合能同時表徵自然與誇張化的虛擬形象。該方案提升了保真度，支持局部編輯，並實現對漫畫化強度的連續控制。為實現實時變形，我們引入了原始表面與誇張表面之間的高效插值方法，並通過分析證明該方法與閉式解存在有界偏差。在定量與定性評估中，我們的成果均超越現有工作，能夠生成幾何可控的照片級真實感漫畫虛擬形象。

English

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.

CaricatureGS：利用高斯曲率誇張化3D高斯潑濺人臉

CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature

摘要

Support