论文标题
自由式井：具有明确目光控制的神经通话头综合
Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
论文作者
论文摘要
我们提出了自由式 - 人物的神经通话头综合系统。我们表明，具有稀疏3D面部标志的造型面孔足以实现最新的生成性能，而无需依赖诸如3D可变形模型的强大统计学先验。除了3D姿势和面部表情外，我们的方法还能够将目光从驾驶演员转移到源身份。我们的完整管道由三个组件组成：一个规范的3D密钥点估计器，它会回归3D姿势和与表达相关的变形，凝视估计网络和建立在Headgan架构上的生成器。我们进一步实验发电机的扩展，以使用注意机制可容纳几次学习，以防万一可用多个源图像。与最新的重演和运动转移模型相比，我们的系统实现了更高的照片真实性，并结合了出色的身份保存，同时提供了明确的凝视控制。
We present Free-HeadGAN, a person-generic neural talking head synthesis system. We show that modeling faces with sparse 3D facial landmarks are sufficient for achieving state-of-the-art generative performance, without relying on strong statistical priors of the face, such as 3D Morphable Models. Apart from 3D pose and facial expressions, our method is capable of fully transferring the eye gaze, from a driving actor to a source identity. Our complete pipeline consists of three components: a canonical 3D key-point estimator that regresses 3D pose and expression-related deformations, a gaze estimation network and a generator that is built upon the architecture of HeadGAN. We further experiment with an extension of our generator to accommodate few-shot learning using an attention mechanism, in case more than one source images are available. Compared to the latest models for reenactment and motion transfer, our system achieves higher photo-realism combined with superior identity preservation, while offering explicit gaze control.
