We present a novel face reconstruction method capable of reconstructing
detailed face geometry, spatially varying face reflectance from a single
monocular image. We build our work upon the recent advances of DNN-based
auto-encoders with differentiable ray tracing image formation, trained in
self-supervised manner. While providing the advantage of learning-based
approaches and real-time reconstruction, the latter methods lacked fidelity. In
this work, we achieve, for the first time, high fidelity face reconstruction
using self-supervised learning only. Our novel coarse-to-fine deep architecture
allows us to solve the challenging problem of decoupling face reflectance from
geometry using a single image, at high computational speed. Compared to
state-of-the-art methods, our method achieves more visually appealing
reconstruction.

本文提出一种能够重建面部几何形状、在单个单目图像中重建时空变化的面部反射的新颖面部重建方法，采用基于 DNN 的自编码器和可微分光线追踪图像构建，同时利用自监督训练方法实现高保真度的面部重建，同时实现了面部反射和几何形状的高度解耦。