PERSE：基於單張肖像的個人化3D生成化身技術

摘要

我們提出PERSE方法，能從參考肖像構建可動畫化的個人化生成式虛擬化身。該虛擬化身模型具備連續且解耦的潛在空間，可透過面部屬性編輯精確控制各項面部特徵，同時保持個體身份識別度。為實現此目標，我們首先生成大規模合成2D影片數據集，每段影片在保持面部表情與視角連貫變化的基礎上，結合原始輸入的特定面部屬性變異。我們提出創新流程來生成高品質、具照片真實感的2D面部屬性編輯影片。基於此合成屬性數據集，我們採用3D高斯潑濺技術開發個人化虛擬化身建構方法，透過學習連續解耦潛在空間實現直觀的面部屬性操控。為確保潛在空間中的平滑過渡，我們引入潛在空間正則化技術，以插值生成的2D面部作為監督信號。相較既有方法，PERSE能生成具有插值屬性的高品質虛擬化身，同時完美保留參考人物的身份特徵。

English

We present PERSE, a method for building an animatable personalized generative avatar from a reference portrait. Our avatar model 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 the facial expression and viewpoint, combined with a variation 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 the 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 identity of reference person.

PERSE：基於單張肖像的個人化3D生成化身技術

PERSE: Personalized 3D Generative Avatars from A Single Portrait

摘要

Support