# EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation

arXiv: https://arxiv.org/abs/2510.08587 · HTML: https://mlsanity.com/paper/2510.08587/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition](https://mlsanity.com/paper/2211.12368/) (2022)
- [Sound Adversarial Audio-Visual Navigation](https://mlsanity.com/paper/2202.10910/) (2022)
- [Measuring Acoustics with Collaborative Multiple Agents](https://mlsanity.com/paper/2310.05368/) (2023)
- [Pay Self-Attention to Audio-Visual Navigation](https://mlsanity.com/paper/2210.01353/) (2022)
- [GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting](https://mlsanity.com/paper/2404.16012/) (2024)

## Built on by (most cited first, 1 of 1)

- [Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation](https://mlsanity.com/paper/2512.13495/) (2025)

## Abstract (arXiv)

This paper presents EGSTalker, a real-time audio-driven talking head generation framework based on 3D Gaussian Splatting (3DGS). Designed to enhance both speed and visual fidelity, EGSTalker requires only 3-5 minutes of training video to synthesize high-quality facial animations. The framework comprises two key stages: static Gaussian initialization and audio-driven deformation. In the first stage, a multi-resolution hash triplane and a Kolmogorov-Arnold Network (KAN) are used to extract spatial features and construct a compact 3D Gaussian representation. In the second stage, we propose an Efficient Spatial-Audio Attention (ESAA) module to fuse audio and spatial cues, while KAN predicts the corresponding Gaussian deformations. Extensive experiments demonstrate that EGSTalker achieves rendering quality and lip-sync accuracy comparable to state-of-the-art methods, while significantly outperforming them in inference speed. These results highlight EGSTalker's potential for real-time multimedia applications.