AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

TL;DR

AniPortrait is a new framework that synthesizes photorealistic portrait animations driven by audio and reference images, using a two-stage process involving 3D landmark extraction and a diffusion model for realistic rendering.

Contribution

It introduces a novel two-stage approach combining 3D landmark extraction and diffusion models for high-quality, controllable portrait animation driven by audio.

Findings

Outperforms existing methods in facial naturalness and visual quality.

Demonstrates high pose diversity and temporal consistency.

Shows potential for facial motion editing and face reenactment.

Abstract

In this study, we propose AniPortrait, a novel framework for generating high-quality animation driven by audio and a reference portrait image. Our methodology is divided into two stages. Initially, we extract 3D intermediate representations from audio and project them into a sequence of 2D facial landmarks. Subsequently, we employ a robust diffusion model, coupled with a motion module, to convert the landmark sequence into photorealistic and temporally consistent portrait animation. Experimental results demonstrate the superiority of AniPortrait in terms of facial naturalness, pose diversity, and visual quality, thereby offering an enhanced perceptual experience. Moreover, our methodology exhibits considerable potential in terms of flexibility and controllability, which can be effectively applied in areas such as facial motion editing or face reenactment. We release code and model weights at https://github.com/scutzzj/AniPortrait