Learning Disentangled Speech- and Expression-Driven Blendshapes for 3D Talking Face Animation

• URL: http://arxiv.org/abs/2510.25234v1
• Date: Wed, 29 Oct 2025 07:29:21 GMT
• Title: Learning Disentangled Speech- and Expression-Driven Blendshapes for 3D Talking Face Animation
• Authors: Yuxiang Mao, Zhijie Zhang, Zhiheng Zhang, Jiawei Liu, Chen Zeng, Shihong Xia,
• Abstract summary: We model facial animation driven by both speech and emotion as a linear additive problem.<n>We learn a set of blendshapes driven by speech and emotion that can be mapped to the expression and jaw pose parameters of the FLAME model.<n>Our approach achieves superior emotional expressivity compared to existing methods, without compromising lip-sync quality.
• Score: 20.91704034858042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Expressions are fundamental to conveying human emotions. With the rapid advancement of AI-generated content (AIGC), realistic and expressive 3D facial animation has become increasingly crucial. Despite recent progress in speech-driven lip-sync for talking-face animation, generating emotionally expressive talking faces remains underexplored. A major obstacle is the scarcity of real emotional 3D talking-face datasets due to the high cost of data capture. To address this, we model facial animation driven by both speech and emotion as a linear additive problem. Leveraging a 3D talking-face dataset with neutral expressions (VOCAset) and a dataset of 3D expression sequences (Florence4D), we jointly learn a set of blendshapes driven by speech and emotion. We introduce a sparsity constraint loss to encourage disentanglement between the two types of blendshapes while allowing the model to capture inherent secondary cross-domain deformations present in the training data. The learned blendshapes can be further mapped to the expression and jaw pose parameters of the FLAME model, enabling the animation of 3D Gaussian avatars. Qualitative and quantitative experiments demonstrate that our method naturally generates talking faces with specified expressions while maintaining accurate lip synchronization. Perceptual studies further show that our approach achieves superior emotional expressivity compared to existing methods, without compromising lip-sync quality.

Related papers

• VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis [70.76837748695841]
  We propose VisualSpeaker, a novel method that bridges the gap using photorealistic differentiable rendering, supervised by visual speech recognition, for improved 3D facial animation.<n>Our contribution is a perceptual lip-reading loss, derived by passing 3D Gaussian Splatting avatar renders through a pre-trained Visual Automatic Speech Recognition model during training.<n> Evaluation on the MEAD dataset demonstrates that VisualSpeaker improves both the standard Lip Vertex Error metric by 56.1% and the perceptual quality of the generated animations, while retaining the controllability of mesh-driven animation.
  arXiv  Detail & Related papers  (2025-07-08T15:04:17Z)
• EmoDiffusion: Enhancing Emotional 3D Facial Animation with Latent Diffusion Models [66.67979602235015]
  EmoDiffusion is a novel approach that disentangles different emotions in speech to generate rich 3D emotional facial expressions.<n>We capture facial expressions under the guidance of animation experts using LiveLinkFace on an iPhone.
  arXiv  Detail & Related papers  (2025-03-14T02:54:22Z)
• GaussianSpeech: Audio-Driven Gaussian Avatars [76.10163891172192]
  We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio.<n>We propose a compact and efficient 3DGS-based avatar representation that generates expression-dependent color and leverages wrinkle- and perceptually-based losses to synthesize facial details.
  arXiv  Detail & Related papers  (2024-11-27T18:54:08Z)
• EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head [30.138347111341748]
  We present a novel approach for synthesizing 3D talking heads with controllable emotion. Our model enables controllable emotion in the generated talking heads and can be rendered in wide-range views. Experiments demonstrate the effectiveness of our approach in generating high-fidelity and emotion-controllable 3D talking heads.
  arXiv  Detail & Related papers  (2024-08-01T05:46:57Z)
• EmoVOCA: Speech-Driven Emotional 3D Talking Heads [12.161006152509653]
  We propose an innovative data-driven technique for creating a synthetic dataset, called EmoVOCA.<n>We then designed and trained an emotional 3D talking head generator that accepts a 3D face, an audio file, an emotion label, and an intensity value as inputs, and learns to animate the audio-synchronized lip movements with expressive traits of the face.
  arXiv  Detail & Related papers  (2024-03-19T16:33:26Z)
• Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape [19.431264557873117]
  We introduce VividTalker, a new framework designed to facilitate speech-driven 3D facial animation. We explicitly disentangle facial animation into head pose and mouth movement and encode them separately. We construct a new 3D dataset with detailed shapes and learn to synthesize facial details in line with speech content.
  arXiv  Detail & Related papers  (2023-10-31T07:47:19Z)
• DF-3DFace: One-to-Many Speech Synchronized 3D Face Animation with Diffusion [68.85904927374165]
  We propose DF-3DFace, a diffusion-driven speech-to-3D face mesh synthesis. It captures the complex one-to-many relationships between speech and 3D face based on diffusion. It simultaneously achieves more realistic facial animation than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-08-23T04:14:55Z)
• Emotional Speech-Driven Animation with Content-Emotion Disentanglement [51.34635009347183]
  We propose EMOTE, which generates 3D talking-head avatars that maintain lip-sync from speech while enabling explicit control over the expression of emotion. EmOTE produces speech-driven facial animations with better lip-sync than state-of-the-art methods trained on the same data.
  arXiv  Detail & Related papers  (2023-06-15T09:31:31Z)
• EMOCA: Emotion Driven Monocular Face Capture and Animation [59.15004328155593]
  We introduce a novel deep perceptual emotion consistency loss during training, which helps ensure that the reconstructed 3D expression matches the expression depicted in the input image. On the task of in-the-wild emotion recognition, our purely geometric approach is on par with the best image-based methods, highlighting the value of 3D geometry in analyzing human behavior.
  arXiv  Detail & Related papers  (2022-04-24T15:58:35Z)

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.