TECHNIQUES FOR SCULPTING DIGITAL FACES BASED ON ANATOMICAL MODELING

Number: 20220005268
Published: 2022-01-06
Filed: 2020-07-06
Assignee: DISNEY ENTERPRISES, INC.
Inventors: GRUBER; Aurel, FRATARCANGELI; Marco, BRADLEY; Derek Edward, ZOSS; Gaspard, BEELER; Dominik Thabo
CPC: G06T7/60; G06T17/20; G06T17/00
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Anatomically-based digital-face sculpting technique.

Abstract

Techniques are disclosed for creating digital faces. In some examples, an anatomical face model is generated from a data set including captured facial geometries of different individuals and associated bone geometries. A model generator segments each of the captured facial geometries into patches, compresses the segmented geometry associated with each patch to determine local deformation subspaces of the anatomical face model, and determines corresponding compressed anatomical subspaces of the anatomical face model. A sculpting application determines, based on sculpting input from a user, constraints for an optimization to determine parameter values associated with the anatomical face model. The parameter values can be used, along with the anatomical face model, to generate facial geometry that reflects the sculpting input.

Background

BACKGROUND Technical Field

Embodiments of the present disclosure relate generally to computer science and computer graphics and, more specifically, to techniques for sculpting digital faces based on anatomical modeling. Description of the Related Art

Realistic digital faces are required for various computer graphics and computer vision applications. For example, digital faces oftentimes are used in the virtual scenes of film productions and in video games.

Digital faces can be created using free-form sculpting tools. Commercially-available sculpting tools, such as ZBrush®, Mudbox®, and Maya®, permit significant artistic freedom in sculpting digital faces by hand. However, manual sculpting of digital faces requires a user to be skilled at free-form sculpting and is oftentimes labor intensive. Using a conventional sculpting tool, a skilled user can spend weeks, or even months, creating a single digital face.

One approach that allows users who are not skilled at free-form sculpting to create digital faces involves generating the digital faces using predetermined libraries of exemplar faces (e.g., blendshape models), from which the users can select and blend different three-dimensional (3D) geometries together, in order to create new faces. However, such an approach limits the digital faces that can be created to the exemplar faces and blendings of those faces. As a result, users may not be able to create digital faces with desired characteristics. [00

Claims

1. A computer-implemented method for generating a digital face, the method comprising: generating a model based on a plurality of facial geometries associated with a plurality of different individuals and a plurality of bone geometries associated with the plurality of different individuals, wherein the model comprises a plurality of local deformation subspaces defining how patches of skin deform and a plurality of anatomical subspaces defining at least one of how the patches slide on underlying bones, in which directions the patches slide, or skin thicknesses associated with the patches; performing one or more optimization operations based on the model and one or more constraints to determine parameter values associated with the model; and generating a three-dimensional (3D) facial geometry based on the parameter values and the model. || 10. One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processing units, cause the one or more processing units to generate a digital face, by performing the steps of: generating a model based on a plurality of facial geometries associated with a plurality of different individuals and a plurality of bone geometries associated with the plurality of different individuals, wherein the model comprises a plurality of local deformation subspaces defining how patches of skin deform and a plurality of anatomical subspaces defining at least one of how the patches slide on underlying bones, which directions the patches slide, or skin thicknesses associated with the patches; performing one or more optimization operations based on the model and one or more constraints to determine parameter values associated with the model; and generating a three-dimensional (3D) facial geometry based on the parameter values and the model. || 19. A system, comprising: one or more memories that include instructions; and one or more processors that are coupled to the one or more memories and, when executing the instructions: generate a model based on a plurality of facial geometries associated with a plurality of different individuals and a plurality of bone geometries associated with the plurality of different individuals, wherein the model comprises a plurality of local deformation subspaces defining how patches of skin deform and a plurality of anatomical subspaces defining at least one of how the patches slide on underlying bones, which directions the patches slide, or skin thicknesses associated with the patches, perform one or more optimization operations based on the model and one or more constraints to determine parameter values associated with the model, and generate a three-dimensional (3D) facial geometry based on the parameter values and the model.