AUTOMATED IMAGE AUGMENTATION USING A VIRTUAL CHARACTER

Number: 20200027271
Published: 2020-01-23
Filed: 2018-07-17
Assignee: DISNEY ENTERPRISES INC.
Inventors: Guay; Martin, Cimen; Gokcen, Maurhofer; Christoph, Ryffel; Mattia, Sumner; Robert
CPC: G06T19/006; G06T7/73
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

ML image augmentation using a virtual character.

Abstract

An image processing system includes a computing platform having a hardware processor and a system memory storing an image augmentation software code, a three-dimensional (3D) shapes library, and/or a 3D poses library. The image processing system also includes a two-dimensional (2D) pose estimation module communicatively coupled to the image augmentation software code. The hardware processor executes the image augmentation software code to provide an image to the 2D pose estimation module and to receive a 2D pose data generated by the 2D pose estimation module based on the image. The image augmentation software code identifies a 3D shape and/or a 3D pose corresponding to the image using an optimization algorithm applied to the 2D pose data and one or both of the 3D poses library and the 3D shapes library, and may output the 3D shape and/or 3D pose to render an augmented image on a display.

Background

BACKGROUND

Augmented reality (AR), in which real world objects and/or environments are digitally augmented with virtual imagery, offers more immersive and enjoyable educational or entertainment experiences.SUMMARY

There are provided systems and methods for performing automated image augmentation using a virtual character, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.

Claims

1. An image processing system comprising: a computing platform including a hardware processor and a system memory; the system memory storing an image augmentation software code and at least one of a three-dimensional (3D) poses library and a 3D shapes library; a two-dimensional (2D) pose estimation module communicatively coupled to the image augmentation software code; the hardware processor configured to execute the image augmentation software code to: provide an image as an input to the 2D pose estimation module; receive from the 2D pose estimation module, a 2D pose data generated based on the image; and identify at least one of a 3D pose and a 3D shape corresponding to the image, based on the 2D pose data, wherein the at least one of the 3D pose and the 3D shape is identified using an optimization algorithm applied to the 2D pose data and the at least one of the 3D poses library and the 3D shapes library. 12. A method for use by an image processing system including a computing platform having a hardware processor and a system memory storing an image augmentation software code and at least one of a three-dimensional (3D) poses library and a 3D shapes library, the method comprising: providing, by the image augmentation software code executed by the hardware processor, an image as an input to a two-dimensional (2D) pose estimation module communicatively coupled to the image augmentation software code; receiving from the 2D pose estimation module, by the image augmentation software code executed by the hardware processor, a 2D pose data generated based on an image; and identifying, by the image augmentation software code executed by the hardware processor, at least one of a 3D pose and a 3D shape corresponding to the image, based on the 2D pose data, wherein the at least one of the 3D pose and the 3D shape is identified using an optimization algorithm applied to the 2D pose data and is the at least one of the 3D poses library and the 3D shapes library.