BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction

TL;DR

BareSkinNet is a novel 3D face reconstruction method that effectively removes makeup and lighting effects from face images, enabling improved face editing and generation applications.

Contribution

It introduces a 3D morphable model-based approach that does not require reference images or lighting conditions, advancing makeup removal and face normalization techniques.

Findings

Outperforms state-of-the-art makeup removal methods

Enables high-fidelity texture map generation for faces

Facilitates 3D face asset creation for artists

Abstract

We propose BareSkinNet, a novel method that simultaneously removes makeup and lighting influences from the face image. Our method leverages a 3D morphable model and does not require a reference clean face image or a specified light condition. By combining the process of 3D face reconstruction, we can easily obtain 3D geometry and coarse 3D textures. Using this information, we can infer normalized 3D face texture maps (diffuse, normal, roughness, and specular) by an image-translation network. Consequently, reconstructed 3D face textures without undesirable information will significantly benefit subsequent processes, such as re-lighting or re-makeup. In experiments, we show that BareSkinNet outperforms state-of-the-art makeup removal methods. In addition, our method is remarkably helpful in removing makeup to generate consistent high-fidelity texture maps, which makes it extendable to many realistic face generation applications. It can also automatically build graphic assets of face makeup images before and after with corresponding 3D data. This will assist artists in accelerating their work, such as 3D makeup avatar creation.