Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single "in-the-wild" image. Nevertheless, to the best of our knowledge, there is no method which can produce high-resolution photorealistic 3D faces from "in-the-wild" images and this can be attributed to the: (a) scarcity of available data for training, and (b) lack of robust methodologies that can successfully be applied on very high-resolution data. In this paper, we introduce AvatarMe, the first method that is able to reconstruct photorealistic 3D faces from a single "in-the-wild" image with an increasing level of detail. To achieve this, we capture a large dataset of facial shape and reflectance and build on a state-of-the-art 3D texture and shape reconstruction method and successively refine its results, while generating the per-pixel diffuse and specular components that are required for realistic rendering. As we demonstrate in a series of qualitative and quantitative experiments, AvatarMe outperforms the existing arts by a significant margin and reconstructs authentic, 4K by 6K-resolution 3D faces from a single low-resolution image that, for the first time, bridges the uncanny valley.

中文翻译：

---

AvatarMe：逼真的可渲染 3D 面部重建“野外”

在过去的几年里，随着生成对抗网络 (GAN) 的出现，许多人脸分析任务取得了惊人的性能，其应用包括但不限于从单个“野外”生成人脸和 3D 人脸重建图像。然而，据我们所知，没有任何方法可以从“野外”图像中生成高分辨率逼真的 3D 人脸，这可以归因于：(a) 可用的训练数据稀缺，以及(b) 缺乏可成功应用于极高分辨率数据的可靠方法。在本文中，我们介绍了 AvatarMe，这是第一种能够从单个“野外”图像中重建逼真 3D 人脸的方法，并且细节水平不断提高。为了达成这个，我们捕获了面部形状和反射率的大型数据集，并建立在最先进的 3D 纹理和形状重建方法的基础上，并不断改进其结果，同时生成逼真渲染所需的每像素漫反射和镜面反射分量。正如我们在一系列定性和定量实验中所证明的那样，AvatarMe 显着优于现有艺术，并从单个低分辨率图像重建真实的 4K x 6K 分辨率 3D 人脸，首次跨越了恐怖谷.