LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space
This work addresses the problem of generating realistic and interpretable emotional expressions in synthetic talking heads for applications like animation or virtual avatars, representing an incremental improvement over existing coarse-grained models.
The paper tackled the lack of fine-grained emotion editing in one-shot talking head generation by proposing LES-Talker, which uses a Linear Emotion Space based on Facial Action Units to enable controllable editing across emotion types, levels, and facial units, achieving high visual quality and outperforming mainstream methods.
While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head generation model with high interpretability, to achieve fine-grained emotion editing across emotion types, emotion levels, and facial units. We propose a Linear Emotion Space (LES) definition based on Facial Action Units to characterize emotion transformations as vector transformations. We design the Cross-Dimension Attention Net (CDAN) to deeply mine the correlation between LES representation and 3D model representation. Through mining multiple relationships across different feature and structure dimensions, we enable LES representation to guide the controllable deformation of 3D model. In order to adapt the multimodal data with deviations to the LES and enhance visual quality, we utilize specialized network design and training strategies. Experiments show that our method provides high visual quality along with multilevel and interpretable fine-grained emotion editing, outperforming mainstream methods.