Artist guided generation of video game production quality face textures. (August 2021)

• Record Type: Journal Article
• Authors: Murphy, Christian; Mudur, Sudhir; Holden, Daniel; Carbonneau, Marc-André; Ghafourzadeh, Donya; Beauchamp, Andre
• Is Part Of: Computers & graphics. Volume 98(2021)
• Page Start: 268
• Page End: 279
• Publication Date: 2021-08
• Subjects: Face texture generation -- Artist guided -- SuperResolution -- BRDF recovery; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2021.06.004
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: Artists can generate face textures using a machine learning based system. Generated face textures are 4K resolution and ready for raytraced rendering. A diverse range of appearances can be generated with very little training data. Graphical abstract: Abstract: We develop a high resolution face texture generation system which uses artist provided appearance controls as the conditions for a generative network. Artists are able to control various elements in the generated textures, such as the skin, eye, lip, and hair color. This is made possible by reparameterizing our dataset to the same UV mapping, allowing us to utilize image-to-image translation networks. Although our dataset is limited in size, only 126 samples in total, our system is still able to generate realistic face textures which strongly adhere to the input appearance attribute conditions because of our training augmentation methods. Once our system has generated the face texture, it is ready to be used in a modern game production environment. Thanks to our novel SuperResolution and material property recovery methods, our generated face textures are 4K resolution and have the associated material property maps required for raytraced rendering.