BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction
This addresses the need for consistent high-fidelity texture maps in realistic face generation applications, such as 3D makeup avatar creation, to assist artists in accelerating their work.
The paper tackles the problem of simultaneously removing makeup and lighting influences from face images by proposing BareSkinNet, which leverages 3D face reconstruction to infer normalized 3D face texture maps, outperforming state-of-the-art makeup removal methods.
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.