EmoHead：通过操纵语义表情参数实现情感说话头部
EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters
AI总结：
提出EmoHead框架，通过情感标签指定的音频-表情模块预测语义表情参数，并利用预训练超平面细化面部运动以正则化神经辐射场，实现了情感一致且具有更好重建质量与可控性的说话头部视频生成。
摘要：
从音频输入生成特定情感的说话头部视频是人机交互中一项重要且复杂的挑战。然而，情感是高度抽象的概念且边界模糊，需要解耦的表情参数来生成富有情感表现力的说话头部视频。在本研究中，我们提出EmoHead，通过语义表情参数合成说话头部视频。为了预测任意音频输入的表情参数，我们应用了一个可由情感标签指定的音频-表情模块。该模块旨在增强跨各种情感的音频输入相关性。此外，我们利用预训练超平面，通过沿垂直方向探测来细化面部运动。最后，细化后的表情参数对神经辐射场进行正则化，并促进说话头部视频的情感一致性生成。实验结果表明，语义表情参数带来了更好的重建质量和可控性。
英文摘要：
Generating emotion-specific talking head videos from audio input is an important and complex challenge for human-machine interaction. However, emotion is highly abstract concept with ambiguous boundaries, and it necessitates disentangled expression parameters to generate emotionally expressive talking head videos. In this work, we present EmoHead to synthesize talking head videos via semantic expression parameters. To predict expression parameter for arbitrary audio input, we apply an audio-expression module that can be specified by an emotion tag. This module aims to enhance correlation from audio input across various emotions. Furthermore, we leverage pre-trained hyperplane to refine facial movements by probing along the vertical direction. Finally, the refined expression parameters regularize neural radiance fields and facilitate the emotion-consistent generation of talking head videos. Experimental results demonstrate that semantic expression parameters lead to better reconstruction quality and controllability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
