BlendFields: Few-Shot Example-Driven Facial Modeling

TL;DR

BlendFields is a novel facial modeling method that captures fine details and generalizes to unseen expressions by blending appearance from sparse extreme poses, bridging the gap between data-driven and geometric approaches.

Contribution

It introduces a technique inspired by computer graphics that models unseen expressions through local volumetric blending, enhancing detail capture beyond existing geometric models.

Findings

Generalizes to unseen expressions with fine-grained effects

Outperforms traditional geometric models in detail preservation

Applicable beyond facial modeling to other deformable objects

Abstract

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.