# RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn Conversation

arXiv: https://arxiv.org/abs/2601.10606 · HTML: https://mlsanity.com/paper/2601.10606/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 15 Jan 2026.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion](https://mlsanity.com/paper/2204.08451/) (2022)
- [SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis](https://mlsanity.com/paper/2311.17590/) (2023)
- [Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis](https://mlsanity.com/paper/2307.09323/) (2023)
- [Sonic: Shifting Focus to Global Audio Perception in Portrait Animation](https://mlsanity.com/paper/2411.16331/) (2024)
- [HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters](https://mlsanity.com/paper/2505.20156/) (2025)
- [SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces](https://mlsanity.com/paper/2306.10799/) (2023)
- [TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting](https://mlsanity.com/paper/2404.15264/) (2024)
- [DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations](https://mlsanity.com/paper/2505.18096/) (2025)
- [EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion](https://mlsanity.com/paper/2411.16726/) (2024)
- [NTO3D: Neural Target Object 3D Reconstruction with Segment Anything](https://mlsanity.com/paper/2309.12790/) (2023)
- [RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network](https://mlsanity.com/paper/2406.18284/) (2024)
- [EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting](https://mlsanity.com/paper/2411.15582/) (2024)
- [GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians](https://mlsanity.com/paper/2412.13983/) (2024)
- [GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.12981/) (2024)
- [Audio-Driven Universal Gaussian Head Avatars](https://mlsanity.com/paper/2509.18924/) (2025)
- [Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters](https://mlsanity.com/paper/2402.13724/) (2024)
- [EmoTalkingGaussian: Continuous Emotion-conditioned Talking Head Synthesis](https://mlsanity.com/paper/2502.00654/) (2025)
- [DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation](https://mlsanity.com/paper/2503.18159/) (2025)
- [MeMo: Attentional Momentum for Real-Time Audio-Visual Target Speaker Extraction Under Impaired Visual Conditions](https://mlsanity.com/paper/2507.15294/) (2025)

## Built on by (most cited first, 2 of 2)

- [AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation](https://mlsanity.com/paper/2605.02948/) (2026)
- [SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation](https://mlsanity.com/paper/2606.03909/) (2026)

## Abstract (arXiv)

Talking head generation is increasingly important in virtual reality (VR), especially for social scenarios involving multi-turn conversation. Existing approaches face notable limitations: mesh-based 3D methods can model dual-person dialogue but lack realistic textures, while large-model-based 2D methods produce natural appearances but incur prohibitive computational costs. Recently, 3D Gaussian Splatting (3DGS) based methods achieve efficient and realistic rendering but remain speaker-only and ignore social relationships. We introduce RSATalker, the first framework that leverages 3DGS for realistic and socially-aware talking head generation with support for multi-turn conversation. Our method first drives mesh-based 3D facial motion from speech, then binds 3D Gaussians to mesh facets to render high-fidelity 2D avatar videos. To capture interpersonal dynamics, we propose a socially-aware module that encodes social relationships, including blood and non-blood as well as equal and unequal, into high-level embeddings through a learnable query mechanism. We design a three-stage training paradigm and construct the RSATalker dataset with speech-mesh-image triplets annotated with social relationships. Extensive experiments demonstrate that RSATalker achieves state-of-the-art performance in both realism and social awareness. The code and dataset will be released.