GemTalk framework enhances emotional talking face generation with geometric control

Researchers have developed GemTalk, a novel diffusion-based framework for generating realistic and controllable emotional talking face videos. This system addresses the limitations of existing methods by integrating implicit representations for semantic richness with explicit geometric priors for structural precision. GemTalk utilizes a Vision-guided Audio Emotion Projection module and a Diffusion-based Geometric Priors Generator to extract and refine emotional and facial expression features, enabling fine-grained control over emotional intensity without compromising visual quality. AI

IMPACT This framework could advance the realism and controllability of AI-generated emotional expressions in video.

RANK_REASON The item is an academic paper detailing a new method for AI-driven video generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• Connected Papers
• CORE Recommender
• DagsHub
• Diffusion-based Geometric Priors Generator
• GemTalk
• Geometry-guided Emotion Modulation
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations
• Vision-guided Audio Emotion Projection

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →