Apple Redefines the original Patent for Creating Motion-Based 3D Facial Models for Animoji and Memoji
Back on June 13, 2019 Patently Apple posted a report titled "Apple's Patent for Creating Motion-Based 3D Facial Models for Memoji was Published Today." The majority of the inventors came from Faceshift that Apple acquired back in 2015.
Apple notes in their patent that motion capture has been used in a variety of areas to generate motion data that is based on tracking and recording the movements of real objects. For example, motion capture technology has been used frequently in video game production and movie production.
Apple began using this patented technology for creating Animoji and Memoji with the introduction of iPhone X using the new TrueDepth camera. In-part, the original introduction of Animoji by Jony Ive is still shown in this Fast Company report, though only as a GIF. The original video isn't available on YouTube.
The images from the GIF above illustrate Ive's face in a raw 3D Motion frame which matches the patent's figures presented below.
Apple's patent FIG. 5 below depicts a representation of a model of a user's face; FIG. 6 depicts a side-by-side representation of an example captured image and an example three-dimensional model projected onto the example captured image; FIG. 7 depicts an example of two three-dimensional models of a user with different poses and expressions in each of the models.
In today's continuation patent, Apple is shown to have cancelled all previous patent claims. This was likely done because, for the most part, the older claims derived from Apple's acquired patent from Faceshift.
The entire 20 patent claims have been rewritten to better reflect Apple's use of them in Animoji and Memoji that wasn't the original intent which was more generic. Below are just a few of the new patent claims in today's continuation patent:
The first patent claim states that the invention covers "A method, comprising: obtaining at least one image of a face of a user using a camera located on a device, the device comprising a computer processor, a memory, and a display; generating one or more first feature vectors from the at least one image, wherein the first feature vectors represent one or more facial features of the face in the at least one image; determining a pose of the face of the user and one or more muscle activations of the face in the at least one image based on the first feature vectors; generating a three-dimensional model of the user's face based on the pose and muscle activations of the face determined from the first feature vectors; generating one or more second feature vectors for the at least one image, wherein the second feature vectors represent one or more facial features of the face at selected locations in the at least one image, wherein the selected locations are determined by defining one or more selected locations on a projection of the three-dimensional model onto the at least one image; and refining, at least once, the generated three-dimensional model of the user's face based on pose and muscle activations for the face refined using the second feature vectors.
Some of the other new patent claims state the following:
… comprising displaying a representation of the three-dimensional model on the display.
… generating and refining three-dimensional models for a plurality of images of the face of the user obtained using the camera; generating an animated three-dimensional model of the user's face based on the refined three-dimensional models generated for the plurality of images; and displaying a representation of the animated three-dimensional model on the display.
… displaying the representation of the animated three-dimensional model on the display includes displaying a simulation of motion of the user's face in the plurality of images.
… determining the pose and muscle activations comprises performing regression on the feature vectors.
… wherein the three-dimensional model is projected onto the at least one image based on parameters of the camera.
… wherein the refining of the generated three-dimensional model of the user's face based on pose and muscle activations for the face refined using the second feature vectors is repeated a selected number of times.
You could review the new 20 patent claims of continuation patent 20200125835 in full here.