论文标题
一张图像的深3D肖像
Deep 3D Portrait from a Single Image
论文作者
论文摘要
在本文中，我们提出了一种基于学习的方法，用于从单个肖像图像中恢复人头的3D几何形状。我们的方法是以无监督的方式学习的，而没有任何基础3D数据。 我们代表具有参数3D面模型的头部几何形状，以及其他头部区域（包括头发和耳朵）的深度图。提出了一个两步的几何学习方案，以从野外面部图像中学习3D头部重建，我们首先使用自我重建来学习单个图像的脸部形状，然后以立体匹配方式使用成对的图像来学习头发和耳朵几何形状。第二步是基于第一个输出，不仅可以提高准确性，还可以确保整体头几何形状的一致性。 我们在3D和2D图像上使用姿势操纵任务评估了我们方法的准确性。我们根据恢复的几何形状更改姿势，并应用一个经过对抗学习训练的改进网络，以改善重新注射的图像并将其转换为真实的图像域。广泛的评估和与先前方法的比较表明，我们的新方法可以产生高保真3D头几何形状和头部姿势操纵结果。
In this paper, we present a learning-based approach for recovering the 3D geometry of human head from a single portrait image. Our method is learned in an unsupervised manner without any ground-truth 3D data. We represent the head geometry with a parametric 3D face model together with a depth map for other head regions including hair and ear. A two-step geometry learning scheme is proposed to learn 3D head reconstruction from in-the-wild face images, where we first learn face shape on single images using self-reconstruction and then learn hair and ear geometry using pairs of images in a stereo-matching fashion. The second step is based on the output of the first to not only improve the accuracy but also ensure the consistency of overall head geometry. We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images. We alter pose based on the recovered geometry and apply a refinement network trained with adversarial learning to ameliorate the reprojected images and translate them to the real image domain. Extensive evaluations and comparison with previous methods show that our new method can produce high-fidelity 3D head geometry and head pose manipulation results.
