Facial animation models

Number: 10964083
Published: 2021-03-30
Filed: 2019-04-10
Assignee: LUCASFILM ENTERTAINMENT COMPANY LTD.
Inventors: Bhat; Kiran S., Koperwas; Michael, Rose; Rachel M., Hong; Jung-Seung, Pighin; Frederic P., Twigg; Christopher David, Phillips; Cary, Sullivan; Steve
CPC: G06T13/40
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Facial animation modeling technique.

Abstract

A system includes a computing device that includes a memory configured to store instructions. The system also includes a processor configured to execute the instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each of the representations includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

Background

TECHNICAL FIELD (1) This document relates to a system for producing animation models such as facial animation models. BACKGROUND OF THE INVENTION (2) Ever increasing computational power allows complex calculations to be tackled with increased efficiency in less time. For example, robust computer systems can execute applications to simulate objects such as fictional characters and even realistic-looking human forms. To visually present such seemingly realistic characters, a significant amount of detail may be included in the simulated objects (e.g., fine wrinkles in the corner of a character's eye). However, even with increased computational power, a considerable amount of time may be needed to produce such levels of detail for simulating objects. Further, some projects may call for multiple characters (e.g., a motion picture that only includes animated characters) and possibly increase production time by multiple folds. BRIEF SUMMARY OF THE INVENTION (3) The described systems and techniques are for efficiently producing an animation model in a “top-down” manner by using collected representations of an object (e.g., electronic scans of different facial expressions as presented by actor). Providing a construction base, the collected representations (e.g., scanned facial expressions) can be actually presented along with other representations (e.g., other facial expressions) by the produced model. (4) In one implementation, rather than painstakingly building a detailed model of a

Claims

1. A method comprising: receiving, by a computer system, a plurality of three-dimensional (3-D) representations of facial expressions; receiving, by the computer system, a 3-D representation of a neutral facial expression; calculating, by the computer system, spatial differences between features of the 3-D representation of the neutral facial expression and corresponding features of the plurality of 3-D representations of the facial expressions by providing the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to a first solver that uses a sparse set of 3-D correspondences between surface points of the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to generate a dense deformation field; generating, by the computer system, a model that is capable of representing each of the facial expressions; wherein the model is generated using the spatial differences. || 8. A system comprising: one or more processors; and one or more memory devices comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: receiving a plurality of three-dimensional (3-D) representations of facial expressions; receiving a 3-D representation of a neutral facial expression; calculating spatial differences between features of the 3-D representation of the neutral facial expression and corresponding features of the plurality of 3-D representations of the facial expressions by providing the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to a first solver that uses a sparse set of 3-D correspondences between surface points of the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to generate a dense deformation field; generating a model that is capable of representing each of the facial expressions; wherein the model is generated using the spatial differences. || 18. A non-transitory, computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a plurality of three-dimensional (3-D) representations of facial expressions; receiving a 3-D representation of a neutral facial expression; calculating spatial differences between features of the 3-D representation of the neutral facial expression and corresponding features of the plurality of 3-D representations of the facial expressions by providing the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to a first solver that uses a sparse set of 3-D correspondences between surface points of the plurality of 3-D representations of the facial expressions and the 3-D representation of the neutral facial expression to generate a dense deformation field; generating a model that is capable of representing each of the facial expressions; wherein the model is generated using the spatial differences.