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

By Hang Zhou, Yasheng Sun, Wayne Wu, Chen Change Loy, Xiaogang Wang, Ziwei Liu. Computer Vision and Pattern Recognition, 2021

465 citations recorded by the source corpus.

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 non-aligned 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.1

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/122d8f3209c8c0e2516181efda7fa6c911ebd70b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset (2022, background): “Moreover, some video generation methods still leverage the frame-level quality while neglecting the temporal information [72,84,100].”
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (2022, methodology): “We think it might be because most of the participants focus on the overall quality of the video, where the blurry and still face videos [28,49] influence their opinions.”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “velopment expands the application of deepfakes to the entire body [9, 45, 46], the generation of deepfakes from a single”
FaceFormer: Speech-Driven 3D Facial Animation with Transformers (2021, methodology): “While aware of extensive 2D-based approaches [10, 11, 16, 18, 23, 29, 49, 59, 66, 70], we focus on animating a 3D model in this work.”
AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis (2021, background): “Recently, many deep-learning-based techniques [35, 42, 10, 58, 7, 43, 48, 59, 21, 57] are proposed to learn the audio-to-face translation by generative adversarial networks (GANs).”