Show simple item record

dc.contributor.authorYang, Xingchaoen_US
dc.contributor.authorTaketomi, Takafumien_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.description.abstractWe 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.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Computer vision; Machine learning; Computer graphics
dc.subjectComputing methodologies → Computer vision
dc.subjectMachine learning
dc.subjectComputer graphics
dc.titleBareSkinNet: De-makeup and De-lighting via 3D Face Reconstructionen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersDigital Human
dc.identifier.pages12 pages

Files in this item


This item appears in the following Collection(s)

  • 41-Issue 7
    Pacific Graphics 2022 - Symposium Proceedings

Show simple item record