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

• URL: http://arxiv.org/abs/2507.12761v1
• Date: Thu, 17 Jul 2025 03:33:46 GMT
• Title: Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation
• Authors: Hanlei Shi, Leyuan Qu, Yu Liu, Di Gao, Yuhua Zheng, Taihao Li,
• Abstract summary: Emotional talking-head generation has emerged as a pivotal research area at the intersection of computer vision and multimodal artificial intelligence.<n>This study proposes the Think-Before-Draw framework to address two key challenges.
• Score: 7.362433184546492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition [7.362433184546492]
  Dynamic Facial Expression Recognition aims to identify human emotions from temporally evolving facial movements.<n>Our method integrates dynamic motion modeling, semantic text refinement, and token-level cross-modal alignment to facilitate the precise localization of emotionally salient features.
  arXiv  Detail & Related papers  (2025-07-16T04:15:06Z)
• MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding [48.54455964043634]
  MEDTalk is a novel framework for fine-grained and dynamic emotional talking head generation.<n>We integrate audio and speech text, predicting frame-wise intensity variations and dynamically adjusting static emotion features to generate realistic emotional expressions.<n>Our generated results can be conveniently integrated into the industrial production pipeline.
  arXiv  Detail & Related papers  (2025-07-08T15:14:27Z)
• Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation [63.94836524433559]
  DICE-Talk is a framework for disentangling identity with emotion and cooperating emotions with similar characteristics.<n>We develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention.<n>Second, we introduce a correlation-enhanced emotion conditioning module with learnable Emotion Banks.<n>Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process.
  arXiv  Detail & Related papers  (2025-04-25T05:28:21Z)
• Controllable Expressive 3D Facial Animation via Diffusion in a Unified Multimodal Space [7.165879904419689]
  We present a diffusion-based framework for controllable expressive 3D facial animation.<n>Our approach introduces two key innovations: (1) a FLAME-centered multimodal emotion binding strategy, and (2) an attention-based latent diffusion model.<n>Our method achieves a 21.6% improvement in emotion similarity while preserving physiologically plausible facial dynamics.
  arXiv  Detail & Related papers  (2025-04-14T01:38:01Z)
• X-Dyna: Expressive Dynamic Human Image Animation [49.896933584815926]
  X-Dyna is a zero-shot, diffusion-based pipeline for animating a single human image.<n>It generates realistic, context-aware dynamics for both the subject and the surrounding environment.
  arXiv  Detail & Related papers  (2025-01-17T08:10:53Z)
• When Words Smile: Generating Diverse Emotional Facial Expressions from Text [72.19705878257204]
  We introduce an end-to-end text-to-expression model that explicitly focuses on emotional dynamics.<n>Our model learns expressive facial variations in a continuous latent space and generates expressions that are diverse, fluid, and emotionally coherent.
  arXiv  Detail & Related papers  (2024-12-03T15:39:05Z)
• GMTalker: Gaussian Mixture-based Audio-Driven Emotional Talking Video Portraits [60.05683966405544]
  We present GMTalker, a Gaussian mixture-based emotional talking portraits generation framework.<n>Specifically, we propose a continuous and disentangled latent space, achieving more flexible emotion manipulation.<n>We also introduce a normalizing flow-based motion generator pretrained on a large dataset to generate diverse head poses, blinks, and eyeball movements.
  arXiv  Detail & Related papers  (2023-12-12T19:03:04Z)
• High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning [43.09015109281053]
  We propose a more flexible and generalized framework for talking face generation. Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space. An Emotion-aware Audio-to-3DMM Convertor is proposed to connect the emotion condition and the audio sequence to structural representation.
  arXiv  Detail & Related papers  (2023-05-04T05:59:34Z)
• Enhancing Cognitive Models of Emotions with Representation Learning [58.2386408470585]
  We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions. Our framework integrates a contextualized embedding encoder with a multi-head probing model. Our model is evaluated on the Empathetic Dialogue dataset and shows the state-of-the-art result for classifying 32 emotions.
  arXiv  Detail & Related papers  (2021-04-20T16:55:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.