# Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

arXiv: https://arxiv.org/abs/2503.14517 · HTML: https://mlsanity.com/paper/2503.14517/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 58 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [Capture, Learning, and Synthesis of 3D Speaking Styles](https://mlsanity.com/paper/1905.03079/) (2019)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis](https://mlsanity.com/paper/2301.13430/) (2023)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)
- [HumanTOMATO: Text-aligned Whole-body Motion Generation](https://mlsanity.com/paper/2310.12978/) (2023)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [Emotional Speech-Driven Animation with Content-Emotion Disentanglement](https://mlsanity.com/paper/2306.08990/) (2023)
- [Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis](https://mlsanity.com/paper/2207.11770/) (2022)
- [Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation](https://mlsanity.com/paper/2401.08559/) (2024)
- [SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis](https://mlsanity.com/paper/2311.17590/) (2023)

## Built on by (most cited first, 12 of 12)

- [DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations](https://mlsanity.com/paper/2505.18096/) (2025)
- [OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers](https://mlsanity.com/paper/2505.21448/) (2025)
- [Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis](https://mlsanity.com/paper/2509.09595/) (2025)
- [KlingAvatar 2.0 Technical Report](https://mlsanity.com/paper/2512.13313/) (2025)
- [Towards Seamless Interaction: Causal Turn-Level Modeling of Interactive 3D Conversational Head Dynamics](https://mlsanity.com/paper/2512.15340/) (2025)
- [From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping](https://mlsanity.com/paper/2512.25066/) (2025)
- [EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head](https://mlsanity.com/paper/2512.05991/) (2025)
- [Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework](https://mlsanity.com/paper/2605.03390/) (2026)
- [EmoZone-Talker: Regional Semantic Control of Audio-Driven 3DGS Talking Heads via Facial Action Units](https://mlsanity.com/paper/2606.15848/) (2026)
- [MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations](https://mlsanity.com/paper/2606.27779/) (2026)
- [KM-Speaker: Keypoint-Based Style Control for High-Quality Speech-Driven 3D Facial Animation and Dialogue Localization](https://mlsanity.com/paper/2606.28568/) (2026)
- [EmotionDialogCN: A Spontaneous Multimodal Dataset for Mandarin Emotional Dialogue](https://mlsanity.com/paper/2608.20905/) (2026)

## Abstract (arXiv)

Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal domain. We propose a diffusion-transformer-based 3D talking face generation model, Cafe-Talk, which simultaneously incorporates coarse- and fine-grained multimodal control conditions. Nevertheless, the entanglement of multiple conditions challenges achieving satisfying performance. To disentangle speech audio and fine-grained conditions, we employ a two-stage training pipeline. Specifically, Cafe-Talk is initially trained using only speech audio and coarse-grained conditions. Then, a proposed fine-grained control adapter gradually adds fine-grained instructions represented by action units (AUs), preventing unfavorable speech-lip synchronization. To disentangle coarse- and fine-grained conditions, we design a swap-label training mechanism, which enables the dominance of the fine-grained conditions. We also devise a mask-based CFG technique to regulate the occurrence and intensity of fine-grained control. In addition, a text-based detector is introduced with text-AU alignment to enable natural language user input and further support multimodal control. Extensive experimental results prove that Cafe-Talk achieves state-of-the-art lip synchronization and expressiveness performance and receives wide acceptance in fine-grained control in user studies. Project page: https://harryxd2018.github.io/cafe-talk/