Photorealistic facial exaggeration by coupling curvature-weighted mesh deformation with anisotropic 3D Gaussian Splatting. Real-time view synthesis, controllable exaggeration, and faithful identity preservation.
We present CaricatureGS, a curvature-aware 3D Gaussian Splatting framework for photorealistic facial caricature. Our method couples a curvature-weighted Poisson deformation on a fitted FLAME mesh with anisotropic 3D Gaussians. We introduce a local affine transfer (LAT) to synthesize pseudo ground-truth for exaggerated views and a joint optimization training scheme across original and caricatured frames. The result is a single 3DGS model that renders identity-faithful faces under controllable exaggeration and novel views at interactive rates.
Given an input videos we fit per-frame FLAME mesh and estimate Gaussian curvature K on it. We exaggerate the shape geometry by solving a Poisson equation weighted by K.
Local Affine Transfer (LAT) warps original frames to the exaggerated projections, yielding supervision for the Gaussians optimization.
Jointly optimize one set of anisotropic 3D Gaussians on original + caricatured frames for consistent geometry & radiance. Alternating between GT and GT* images allows for smooth interpolation between representations.


@article{Matmon2026CaricatureGS,
title = {CaricatureGS: Gaussian-Curvature-Guided 3D Gaussian Splatting for Facial Caricature},
author = {Matmon Eldad , Bracha Amit, Rotstein Noam, Kimmel Ron},
conference = {3DV},
year = {2026},
note = {submitted}
}