Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning
This work addresses the problem of inconsistent visual quality in talking face video generation for digital human technology, representing an incremental improvement by focusing on uncertainty learning.
The paper tackled the challenge of generating talking face videos from arbitrary speech audio by addressing visual uncertainty, which causes inconsistent quality and unreliable performance, and proposed a Joint Uncertainty Learning Network (JULNet) that jointly optimizes error and uncertainty to enhance model robustness, achieving superior high-fidelity and audio-lip synchronization compared to previous methods.
Talking face video generation with arbitrary speech audio is a significant challenge within the realm of digital human technology. The previous studies have emphasized the significance of audio-lip synchronization and visual quality. Currently, limited attention has been given to the learning of visual uncertainty, which creates several issues in existing systems, including inconsistent visual quality and unreliable performance across different input conditions. To address the problem, we propose a Joint Uncertainty Learning Network (JULNet) for high-quality talking face video generation, which incorporates a representation of uncertainty that is directly related to visual error. Specifically, we first design an uncertainty module to individually predict the error map and uncertainty map after obtaining the generated image. The error map represents the difference between the generated image and the ground truth image, while the uncertainty map is used to predict the probability of incorrect estimates. Furthermore, to match the uncertainty distribution with the error distribution through a KL divergence term, we introduce a histogram technique to approximate the distributions. By jointly optimizing error and uncertainty, the performance and robustness of our model can be enhanced. Extensive experiments demonstrate that our method achieves superior high-fidelity and audio-lip synchronization in talking face video generation compared to previous methods.