BlendFields: Few-Shot Example-Driven Facial Modeling

Autor: Kania, Kacper, Garbin, Stephan J., Tagliasacchi, Andrea, Estellers, Virginia, Yi, Kwang Moo, Valentin, Julien, Trzciński, Tomasz, Kowalski, Marek
Rok vydání: 2023
Předmět:
Druh dokumentu: Working Paper
Popis: Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance. Existing methods are either data-driven, requiring an extensive corpus of data not publicly accessible to the research community, or fail to capture fine details because they rely on geometric face models that cannot represent fine-grained details in texture with a mesh discretization and linear deformation designed to model only a coarse face geometry. We introduce a method that bridges this gap by drawing inspiration from traditional computer graphics techniques. Unseen expressions are modeled by blending appearance from a sparse set of extreme poses. This blending is performed by measuring local volumetric changes in those expressions and locally reproducing their appearance whenever a similar expression is performed at test time. We show that our method generalizes to unseen expressions, adding fine-grained effects on top of smooth volumetric deformations of a face, and demonstrate how it generalizes beyond faces.
Comment: Accepted to CVPR 2023. Project page: https://blendfields.github.io/
Databáze: arXiv