Techniques for removing and synthesizing secondary dynamics in facial performance capture

Number: 11151767
Published: 2021-10-19
Filed: 2020-07-02
Assignee: Disney Enterprises, Inc.
Inventors: Zoss; Gaspard, Sifakis; Eftychios, Beeler; Dominik Thabo, Bradley; Derek Edward
CPC: G06T17/00; G06T7/246; G06T13/40
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

VFX facial performance-capture secondary-dynamics technique.

Abstract

A removal model is trained to predict secondary dynamics associated with an individual enacting a performance. For a given sequence of frames that includes an individual enacting a performance and secondary dynamics, a retargeting application identifies a set of rigid points that correspond to skeletal regions of the individual and a set of non-rigid points that correspond to non-skeletal region of the individual.

Background

BACKGROUND Technical Field (1) Embodiments of the present disclosure relate generally to computer science and computer graphics and, more specifically, to techniques for removing and synthesizing secondary dynamics in facial performance capture.

Claims

1. A computer-implemented method for generating a computer animation, the method comprising: determining, with respect to an object included in a first frame of a sequence of frames, a first set of points associated with at least one non-rigid region of the object and a second set of points associated with at least one rigid region within the object, wherein the first frame includes one or more secondary dynamics; and computing, via at least a first machine learning model, one or more displacements for the first set of points that reduce the one or more secondary dynamics included in the first frame. || 10. A computer-implemented method for generating a computer animation, the method comprising: receiving a first set of points associated with at least one non-rigid region of an object and a second set of points associated with at least one rigid region within the object in a first frame of a sequence of frames; and computing, via at least a first machine learning model, one or more displacements for the first set of points that add one or more secondary dynamics. || 18. 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 perform steps for generating a computer animation, the steps comprising: determining, with respect to an object included in a first frame of a sequence of frames, a first set of points and a second set of points; and computing, via at least a first machine learning model, one or more displacements for the first set of points that reduce the one or more secondary dynamics.