FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model

TL;DR

FD2Talk introduces a facial decoupled diffusion model for talking head generation, effectively separating motion and appearance to improve quality, diversity, and accuracy over previous methods.

Contribution

The paper proposes a novel multi-stage diffusion framework that decouples facial motion and appearance, enhancing generation quality and detail preservation in talking head synthesis.

Findings

Outperforms previous state-of-the-art methods in quality and diversity.

Accurately predicts facial motion from audio using Diffusion Transformer.

Effectively encodes appearance to guide realistic frame generation.

Abstract

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape problem. Although diffusion models show impressive generative ability, their exploration in talking head generation remains unsatisfactory. This is because they either solely use the diffusion model to obtain an intermediate representation and then employ another pre-trained renderer, or they overlook the feature decoupling of complex facial details, such as expressions, head poses and appearance textures. Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages. Specifically, we separate facial details into motion and appearance. In the initial phase, we design the Diffusion Transformer to accurately predict motion coefficients from raw audio. These motions are highly decoupled from appearance, making them easier for the network to learn compared to high-dimensional RGB images. Subsequently, in the second phase, we encode the reference image to capture appearance textures. The predicted facial and head motions and encoded appearance then serve as the conditions for the Diffusion UNet, guiding the frame generation. Benefiting from decoupling facial details and fully leveraging diffusion models, extensive experiments substantiate that our approach excels in enhancing image quality and generating more accurate and diverse results compared to previous state-of-the-art methods.