论文标题
从单个图像中对人脸的正常和可见性估计
Normal and Visibility Estimation of Human Face from a Single Image
论文作者
论文摘要
关于人类内在形象的最新工作开始考虑入射照明的可见性，并通过球形谐波编码光传递函数。在本文中，我们表明，可以将这种光传递函数进一步分解为与表面正常相关的余弦术语。这种分解使我们除了可见性外还可以恢复正常表面。我们提出了一种基于深度学习的方法，并通过对现实世界图像进行培训的重建损失。结果表明，与以前的作品相比，从我们的方法中重建人脸可以更好地揭示表面正常和阴影细节，尤其是在可见性效果强的区域周围。
Recent work on the intrinsic image of humans starts to consider the visibility of incident illumination and encodes the light transfer function by spherical harmonics. In this paper, we show that such a light transfer function can be further decomposed into visibility and cosine terms related to surface normal. Such decomposition allows us to recover the surface normal in addition to visibility. We propose a deep learning-based approach with a reconstruction loss for training on real-world images. Results show that compared with previous works, the reconstruction of human face from our method better reveals the surface normal and shading details especially around regions where visibility effect is strong.
