Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation

TL;DR

This paper introduces a novel framework for generating pose-controllable talking faces from a single image, effectively handling pose control, lip synchronization, and extreme view robustness without relying on structural estimations.

Contribution

The proposed method models audio-visual representations with an implicit pose code, enabling accurate pose control and lip synchronization directly from raw images, surpassing previous landmark-based approaches.

Findings

Accurately lip-synced talking faces with controllable poses.

Robustness to extreme viewing angles.

Effective frontalization of talking faces.

Abstract

While accurate lip synchronization has been achieved for arbitrary-subject audio-driven talking face generation, the problem of how to efficiently drive the head pose remains. Previous methods rely on pre-estimated structural information such as landmarks and 3D parameters, aiming to generate personalized rhythmic movements. However, the inaccuracy of such estimated information under extreme conditions would lead to degradation problems. In this paper, we propose a clean yet effective framework to generate pose-controllable talking faces. We operate on raw face images, using only a single photo as an identity reference. The key is to modularize audio-visual representations by devising an implicit low-dimension pose code. Substantially, both speech content and head pose information lie in a joint non-identity embedding space. While speech content information can be defined by learning the intrinsic synchronization between audio-visual modalities, we identify that a pose code will be complementarily learned in a modulated convolution-based reconstruction framework. Extensive experiments show that our method generates accurately lip-synced talking faces whose poses are controllable by other videos. Moreover, our model has multiple advanced capabilities including extreme view robustness and talking face frontalization. Code, models, and demo videos are available at https://hangz-nju-cuhk.github.io/projects/PC-AVS.