Generative Models

EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation

EmoSpaceTime decouples emotion and content in 3D speech animation through contrastive learning, enabling fine-grained control over emotional expressivity independent of spoken …

p.-witzig

• Nov 21, 2024 • 1 min read

Facial Animation

Facial Animation Synthesis

Efficient transformer-based pipelines for text-driven and speech-driven 3D facial animation — achieving real-time performance through phoneme-level speech modeling and contrastive …

Jan 1, 2024 • 2 min read

No results found

Generative Models

EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation

Facial Animation Synthesis