论文标题
Headgan：单发神经头合成和编辑
HeadGAN: One-shot Neural Head Synthesis and Editing
论文作者
论文摘要
最近使用单个参考图像解决头部重演问题的尝试显示出令人鼓舞的结果。但是，他们中的大多数在照片真实主义方面的表现较差，或者无法解决身份保存问题，或者不能完全传递驾驶姿势和表达。我们提出了HeadGan，这是一个新型系统，它可以在3D面表示上综合，可以从任何驾驶视频中提取并适应任何参考图像的面部几何形状，从而将身份与表达式脱离状态。我们通过利用音频功能作为互补输入来进一步改善口腔运动。 3D面表示使HeadGan可以进一步用作有效的压缩和重建方法，以及表达和姿势编辑的工具。
Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results. However, most of them either perform poorly in terms of photo-realism, or fail to meet the identity preservation problem, or do not fully transfer the driving pose and expression. We propose HeadGAN, a novel system that conditions synthesis on 3D face representations, which can be extracted from any driving video and adapted to the facial geometry of any reference image, disentangling identity from expression. We further improve mouth movements, by utilising audio features as a complementary input. The 3D face representation enables HeadGAN to be further used as an efficient method for compression and reconstruction and a tool for expression and pose editing.
