MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions

TL;DR

MODA introduces a unified system for high-fidelity, multi-person audio-driven portrait animation that effectively captures diverse facial motions and head movements, resulting in more natural and realistic video portraits.

Contribution

The paper presents MODA, a novel mapping-once network with dual attentions for synchronized lip and head movements, advancing the realism of audio-driven portrait synthesis.

Findings

Produces more natural and realistic video portraits

Effectively captures diverse facial motions and head movements

Outperforms previous methods in quality and stability

Abstract

Audio-driven portrait animation aims to synthesize portrait videos that are conditioned by given audio. Animating high-fidelity and multimodal video portraits has a variety of applications. Previous methods have attempted to capture different motion modes and generate high-fidelity portrait videos by training different models or sampling signals from given videos. However, lacking correlation learning between lip-sync and other movements (e.g., head pose/eye blinking) usually leads to unnatural results. In this paper, we propose a unified system for multi-person, diverse, and high-fidelity talking portrait generation. Our method contains three stages, i.e., 1) Mapping-Once network with Dual Attentions (MODA) generates talking representation from given audio. In MODA, we design a dual-attention module to encode accurate mouth movements and diverse modalities. 2) Facial composer network generates dense and detailed face landmarks, and 3) temporal-guided renderer syntheses stable videos. Extensive evaluations demonstrate that the proposed system produces more natural and realistic video portraits compared to previous methods.