论文标题
通过姿势指导网络学习3D面部重建
Learning 3D Face Reconstruction with a Pose Guidance Network
论文作者
论文摘要
我们提出了一种通过姿势指导网络（PGN）学习单程3D面对重建的自我监督学习方法。首先，我们在先前的参数3D面部学习方法中揭示了姿势估计的瓶颈，并建议利用3D面部标志来估计姿势参数。借助我们设计的PGN，我们的模型可以从两张面孔中学习，并具有完全标记的3D地标和无标记的野外面部图像。通过一种自制的学习方案进一步增强了我们的网络，该方案利用嵌入了同一个人多个帧的面部几何信息，以减轻从单个图像中回归3D面部几何形状的不足的性质。这三个见解产生了一种方法，该方法结合了参数模型学习和数据驱动学习技术的互补优势。我们对具有挑战性的AFLW2000-3D，Florence和Facewarehouse数据集进行了严格的评估，并表明我们的方法优于所有指标的最先进。
We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN). First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to utilize 3D face landmarks for estimating pose parameters. With our specially designed PGN, our model can learn from both faces with fully labeled 3D landmarks and unlimited unlabeled in-the-wild face images. Our network is further augmented with a self-supervised learning scheme, which exploits face geometry information embedded in multiple frames of the same person, to alleviate the ill-posed nature of regressing 3D face geometry from a single image. These three insights yield a single approach that combines the complementary strengths of parametric model learning and data-driven learning techniques. We conduct a rigorous evaluation on the challenging AFLW2000-3D, Florence and FaceWarehouse datasets, and show that our method outperforms the state-of-the-art for all metrics.
