Normal and Visibility Estimation of Human Face from a Single Image
This work addresses the challenge of detailed 3D face reconstruction from 2D images for applications in computer vision and graphics, representing an incremental improvement over prior methods.
The paper tackled the problem of estimating surface normal and visibility from a single human face image by decomposing the light transfer function into visibility and cosine terms, resulting in improved reconstruction that better reveals surface normal and shading details, especially in regions with strong visibility effects.
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.