Abstract
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 inter pretable fine-grained emotion editing, outperforming mainstream methods. Project page: https://peterfanfan.github.io/LES-Talker/
Funding Information
  • National Natural Science Foundation of China (62272364)
  • National Natural Science Foundation of China (62472342)
  • Provincial Key Research and Development Program of Shaanxi (2024GH-ZDXM-47)
  • Higher Education Science Research Planning Project of China Association of Higher Education (24PG0101)
  • China Adult Education Association Project (2023-886ZB)
  • Shaanxi Higher Education Teaching Reform Research Project (25BY055)
  • China Education Society of Electronics Teaching Reform Project (DJZ25005)
  • Teaching Reform Project of the Chinese Society for Educational Development Strategy (ZLB20250728)
  • Xidian University Graduate Teaching Reform Project (AIZS2501)