CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature
Eldad Matmon, Amit Bracha, Noam Rotstein, Ron Kimmel

TL;DR
This paper introduces CaricatureGS, a novel framework that combines Gaussian curvature-based surface exaggeration with 3D Gaussian Splatting to produce photorealistic, controllable 3D caricature faces with real-time deformation capabilities.
Contribution
It presents a new method integrating intrinsic curvature exaggeration with 3D Gaussian Splatting, enabling high-fidelity, controllable caricature face avatars with efficient real-time deformation.
Findings
Outperforms prior methods in realism and control.
Supports continuous caricature exaggeration.
Enables real-time avatar deformation.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Face recognition and analysis · 3D Shape Modeling and Analysis
