Samsung Advanced Institute of Technology, Giheung-gu, Yongin-si Gyeonggi-do, 446-712 South Korea.
IEEE Trans Pattern Anal Mach Intell. 2012 Dec;34(12):2341-50. doi: 10.1109/TPAMI.2011.275.
In this paper, we propose a novel method for generating a realistic 3D human face from a single 2D face image for the purpose of synthesizing new 2D face images at arbitrary poses using gender and ethnicity specific models. We employ the Generic Elastic Model (GEM) approach, which elastically deforms a generic 3D depth-map based on the sparse observations of an input face image in order to estimate the depth of the face image. Particularly, we show that Gender and Ethnicity specific GEMs (GE-GEMs) can approximate the 3D shape of the input face image more accurately, achieving a better generalization of 3D face modeling and reconstruction compared to the original GEM approach. We qualitatively validate our method using publicly available databases by showing each reconstructed 3D shape generated from a single image and new synthesized poses of the same person at arbitrary angles. For quantitative comparisons, we compare our synthesized results against 3D scanned data and also perform face recognition using synthesized images generated from a single enrollment frontal image. We obtain promising results for handling pose and expression changes based on the proposed method.
在本文中，我们提出了一种新的方法，从单张 2D 人脸图像生成逼真的 3D 人脸，以便使用特定于性别和种族的模型在任意姿势下合成新的 2D 人脸图像。我们采用了通用弹性模型（GEM）方法，该方法基于输入人脸图像的稀疏观察对通用 3D 深度图进行弹性变形，以估计人脸图像的深度。特别地，我们表明，特定于性别和种族的 GEM（GE-GEM）可以更准确地逼近输入人脸图像的 3D 形状，与原始 GEM 方法相比，实现了更好的 3D 人脸建模和重建的泛化能力。我们使用公开可用的数据库进行了定性验证，展示了从单张图像生成的每个重建 3D 形状以及同一人的任意角度的新合成姿势。为了进行定量比较，我们将我们的合成结果与 3D 扫描数据进行了比较，并且还使用从单个注册正面图像生成的合成图像进行了人脸识别。我们基于所提出的方法获得了处理姿态和表情变化的有希望的结果。
