论文标题
多用途：带有神经隐式功能的单图像中的3D头部肖像
Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions
论文作者
论文摘要
我们提出了一种从一个或几种视图中重建人头的纹理3D网眼的方法。由于如此少的重建量不足，因此需要先验知识，这很难将传统的3D重建算法强加于。在这项工作中，我们依靠最近引入的3D表示$ \ unicode {x2013} $神经隐式函数$ \ unicode {x2013} $，该功能以神经网络为基础，可以自然地从数据中学习有关人头的先验，并直接转换为文本的网状网。也就是说，我们扩展了Neus（一种最新的神经隐式功能制定，以同时代表类的多个对象（在我们的情况下）。潜在的神经网架构旨在学习这些对象之间的共同点，并概括地看不见。我们的模型仅在一百个智能手机视频上进行培训，不需要任何扫描的3D数据。之后，该模型可以以几种或单发模式的方式适合新颖的头部，并以良好的效果。
We present an approach for the reconstruction of textured 3D meshes of human heads from one or few views. Since such few-shot reconstruction is underconstrained, it requires prior knowledge which is hard to impose on traditional 3D reconstruction algorithms. In this work, we rely on the recently introduced 3D representation $\unicode{x2013}$ neural implicit functions $\unicode{x2013}$ which, being based on neural networks, allows to naturally learn priors about human heads from data, and is directly convertible to textured mesh. Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously. The underlying neural net architecture is designed to learn the commonalities among these objects and to generalize to unseen ones. Our model is trained on just a hundred smartphone videos and does not require any scanned 3D data. Afterwards, the model can fit novel heads in the few-shot or one-shot modes with good results.
