Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shi, Hanlei, Qu, Leyuan, Liu, Yu, Gao, Di, Zheng, Yuhua, Li, Taihao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912488256176128
author Shi, Hanlei
Qu, Leyuan
Liu, Yu
Gao, Di
Zheng, Yuhua
Li, Taihao
author_facet Shi, Hanlei
Qu, Leyuan
Liu, Yu
Gao, Di
Zheng, Yuhua
Li, Taihao
contents Emotional talking-head generation has emerged as a pivotal research area at the intersection of computer vision and multimodal artificial intelligence, with its core value lying in enhancing human-computer interaction through immersive and empathetic engagement.With the advancement of multimodal large language models, the driving signals for emotional talking-head generation has shifted from audio and video to more flexible text. However, current text-driven methods rely on predefined discrete emotion label texts, oversimplifying the dynamic complexity of real facial muscle movements and thus failing to achieve natural emotional expressiveness.This study proposes the Think-Before-Draw framework to address two key challenges: (1) In-depth semantic parsing of emotions--by innovatively introducing Chain-of-Thought (CoT), abstract emotion labels are transformed into physiologically grounded facial muscle movement descriptions, enabling the mapping from high-level semantics to actionable motion features; and (2) Fine-grained expressiveness optimization--inspired by artists' portrait painting process, a progressive guidance denoising strategy is proposed, employing a "global emotion localization--local muscle control" mechanism to refine micro-expression dynamics in generated videos.Our experiments demonstrate that our approach achieves state-of-the-art performance on widely-used benchmarks, including MEAD and HDTF. Additionally, we collected a set of portrait images to evaluate our model's zero-shot generation capability.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12761
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation
Shi, Hanlei
Qu, Leyuan
Liu, Yu
Gao, Di
Zheng, Yuhua
Li, Taihao
Computer Vision and Pattern Recognition
Artificial Intelligence
Emotional talking-head generation has emerged as a pivotal research area at the intersection of computer vision and multimodal artificial intelligence, with its core value lying in enhancing human-computer interaction through immersive and empathetic engagement.With the advancement of multimodal large language models, the driving signals for emotional talking-head generation has shifted from audio and video to more flexible text. However, current text-driven methods rely on predefined discrete emotion label texts, oversimplifying the dynamic complexity of real facial muscle movements and thus failing to achieve natural emotional expressiveness.This study proposes the Think-Before-Draw framework to address two key challenges: (1) In-depth semantic parsing of emotions--by innovatively introducing Chain-of-Thought (CoT), abstract emotion labels are transformed into physiologically grounded facial muscle movement descriptions, enabling the mapping from high-level semantics to actionable motion features; and (2) Fine-grained expressiveness optimization--inspired by artists' portrait painting process, a progressive guidance denoising strategy is proposed, employing a "global emotion localization--local muscle control" mechanism to refine micro-expression dynamics in generated videos.Our experiments demonstrate that our approach achieves state-of-the-art performance on widely-used benchmarks, including MEAD and HDTF. Additionally, we collected a set of portrait images to evaluate our model's zero-shot generation capability.
title Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.12761