EmoDiffTalk：面向可编辑 3D 高斯说话头的情感感知扩散模型
EmoDiffTalk: Emotion-aware Diffusion for Editable 3D Gaussian Talking Head
把扩散过程放到 3D 高斯泼溅的表情参数空间（AU 空间）里做去噪，并用文本到 AU 的控制器提供连续可编辑条件——做 3D 说话头或表情编辑时，这种「在低维表情空间做扩散 + 多模态条件注入」的范式可直接复用。
原文依据 a novel Emotion-aware Gaussian Diffusion, which includes an action unit (AU) prompt Gaussian diffusion process for fine-grained facial animator
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期基于 3D 高斯泼溅的照片级真实感 3D 说话头在情感表达操控方面仍存在明显不足，尤其是在利用多模态控制进行细粒度且幅度较大的动态情感编辑时。本文提出一种新的可编辑 3D 高斯说话头，即 EmoDiffTalk。其核心思想是一种新颖的情感感知高斯扩散，包含用于细粒度面部动画的动作单元（AU）提示词高斯扩散过程，以及一个准确的文本到 AU 情感控制器，从而借助文本输入提供准确且幅度可扩展的动态情感编辑。在公开的 EmoTalk3D 与 RenderMe-360 数据集上的实验表明，EmoDiffTalk 在情感细腻度、唇形同步保真度与可控性上均优于先前工作，为高质量、扩散驱动、多模态可编辑的 3D 说话头合成建立了一条有原则的路径。据我们所知，EmoDiffTalk 是首批 3D 高斯泼溅说话头生成框架之一，尤其支持在基于 AU 的表情空间内进行连续的多模态情感编辑。更多细节与信息请访问我们的网站：https://liuchang883.github.io/EmoDiffTalk/
英文原文摘要 1226 字符
Recent photo-realistic 3D talking head via 3D Gaussian Splatting still has significant shortcoming in emotional expression manipulation, especially for fine-grained and expansive dynamics emotional editing using multi-modal control. This paper introduces a new editable 3D Gaussian talking head, i.e. EmoDiffTalk. Our key idea is a novel Emotion-aware Gaussian Diffusion, which includes an action unit (AU) prompt Gaussian diffusion process for fine-grained facial animator, and moreover an accurate text-to-AU emotion controller to provide accurate and expansive dynamic emotional editing using text input. Experiments on public EmoTalk3D and RenderMe-360 datasets demonstrate superior emotional subtlety, lip-sync fidelity, and controllability of our EmoDiffTalk over previous works, establishing a principled pathway toward high-quality, diffusion-driven, multimodal editable 3D talking-head synthesis. To our best knowledge, our EmoDiffTalk is one of the first few 3D Gaussian Splatting talking-head generation framework, especially supporting continuous, multimodal emotional editing within the AU-based expression space.Please visit our website for more details and information:https://liuchang883.github.io/EmoDiffTalk/