SIDER: Single-image neural optimization for facial geometric detail recovery

Abstract

In this work we present Sider, a method for high-fidelity detailed 3D face reconstruction from a single image that can be trained in an unsupervised manner. Our approach combines the best from classical statistical models and recent implicit neural representations. The former is used to obtain a coarse shape prior, and the latter provides high-frequency geometric detail, by only optimizing over a photometric loss computed w.r.t. the input image. A thorough quantitative and qualitative evaluation shows that Sider outperforms current state-of-the-art by a significant margin. A limitation of our current approach is that it still cannot handle details like hair or beards and accessories such as glasses. This is because the photometric loss for these regions would require sub-pixel accuracy. In the future, we will explore alternatives for addressing this type of high-frequency details.