PERSE: Personalized 3D Generative Avatars from A Single Portrait

TL;DR

PERSE introduces a novel method for creating personalized 3D avatars from a single portrait, enabling realistic facial attribute editing while maintaining identity, through synthetic video datasets and 3D Gaussian Splatting.

Contribution

The paper presents a new pipeline combining synthetic 2D video generation and 3D Gaussian Splatting to produce high-quality, editable 3D avatars from a single image, with a focus on disentangled attribute control.

Findings

High-quality, photorealistic 2D videos with attribute editing generated

Disentangled latent space enables intuitive facial attribute manipulation

Preserves individual identity during attribute interpolation

Abstract

We present PERSE, a method for building a personalized 3D generative avatar from a reference portrait. Our avatar enables facial attribute editing in a continuous and disentangled latent space to control each facial attribute, while preserving the individual's identity. To achieve this, our method begins by synthesizing large-scale synthetic 2D video datasets, where each video contains consistent changes in facial expression and viewpoint, along with variations in a specific facial attribute from the original input. We propose a novel pipeline to produce high-quality, photorealistic 2D videos with facial attribute editing. Leveraging this synthetic attribute dataset, we present a personalized avatar creation method based on 3D Gaussian Splatting, learning a continuous and disentangled latent space for intuitive facial attribute manipulation. To enforce smooth transitions in this latent space, we introduce a latent space regularization technique by using interpolated 2D faces as supervision. Compared to previous approaches, we demonstrate that PERSE generates high-quality avatars with interpolated attributes while preserving the identity of the reference individual.