EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model
This work addresses the challenge of generating and editing intricate emotional expressions in talking faces for applications like virtual avatars, though it appears incremental in its method improvements.
The paper tackled the problem of generating talking faces with limited generalization and single-emotion editing by proposing EmoTalker, a diffusion model-based approach that modifies the denoising process and uses an Emotion Intensity Block, resulting in high-quality, emotionally customizable facial expressions.
In recent years, the field of talking faces generation has attracted considerable attention, with certain methods adept at generating virtual faces that convincingly imitate human expressions. However, existing methods face challenges related to limited generalization, particularly when dealing with challenging identities. Furthermore, methods for editing expressions are often confined to a singular emotion, failing to adapt to intricate emotions. To overcome these challenges, this paper proposes EmoTalker, an emotionally editable portraits animation approach based on the diffusion model. EmoTalker modifies the denoising process to ensure preservation of the original portrait's identity during inference. To enhance emotion comprehension from text input, Emotion Intensity Block is introduced to analyze fine-grained emotions and strengths derived from prompts. Additionally, a crafted dataset is harnessed to enhance emotion comprehension within prompts. Experiments show the effectiveness of EmoTalker in generating high-quality, emotionally customizable facial expressions.