IMAGE STYLE TRANSFER

Number: 20250245878
Published: 2025-07-31
Filed: 2024-01-29
Assignee: DISNEY ENTERPRISES, INC.
Inventors: Pernias Pascual de Pobil; Pablo et al.
CPC: G06T11/10
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Creative-ML image style-transfer technique.

Abstract

Techniques for generating modified images using content information and style information are disclosed. First image data comprising image content information is received, and a content encoder generates a first embedding by extracting the image content information from the first image data. A second embedding generated by a style encoder is received, the second embedding comprising style information of second image data. The style information comprises color information and texture information. A decoder generates a modified image using the first embedding and the second embedding, the modified image comprising the image content information of the first image data and the style information of the second image data.

Background

CROSS REFERENCE TO RELATED APPLICATION

This application is related to the Applicant's concurrently filed application titled “Facial Image Swapping,” which is incorporated herein by reference in its entirety for all purposes. FIELD

Described embodiments relate generally to generating modified images, such as modified images comprising content information of a first image and style information of a second image. BACKGROUND

Digital images can be modified in various ways to generate modified images. For example, modified images can be generated to combine characteristics or content of images. Images can also be modified by adding or removing content. Image manipulations can be applied manually or using various algorithms. Current processes do not enable true blending of image content (e.g., person or object representations) to be modified in various styles and allow a user to change the amount of style influence on the modified content. SUMMARY

The following Summary is for illustrative purposes only and does not limit the scope of the technology disclosed in this document.

In an embodiment, a computer-implemented method of generating modified images using content information and style information is disclosed. First image data is received including image content information. The image content information can include positional information of a set of features in the first image data. A first embedding (e.g., a content embedding) is generated usi

Claims

1. A computer-implemented method of generating modified images using content information and style information, the method comprising: receiving first image data comprising image content information; generating, using a content encoder, a first embedding comprising the image content information, wherein the content encoder extracts the image content information from the first image data to generate the first embedding; receiving a second embedding generated by a style encoder, the second embedding comprising style information of second image data, wherein the style information comprises color information and texture information; and generating, by a decoder, a modified image using the first embedding and the second embedding, wherein the modified image comprises the image content information of the first image data and the style information of the second image data. || 8. A non-transitory computer-readable medium carrying instructions that, when executed by a computing system, cause the computing system to perform operations comprising: receive first image data comprising image content information; generate, using a content encoder, a content embedding comprising the image content information, wherein the content encoder extracts the image content information from the first image data to generate the content embedding; receive a style embedding generated by a style encoder, the style embedding comprising style information of second image data, wherein the style information comprises color information and texture information; and generate, by a decoder, a modified image using the content embedding and the style embedding, wherein the modified image comprises the image content information of the first image data and the style information of the second image data. || 15. A computing system comprising: at least one processor; and at least one non-transitory memory carrying instructions that, when executed by the at least one processor, cause the computing system to perform operations comprising: receive first image data comprising image content information; generate, using a content encoder, a content embedding comprising the image content information, wherein the content encoder extracts the image content information from the first image data to generate the content embedding; receive a style embedding generated by a style encoder, the style embedding comprising style information of second image data, wherein the style information comprises color information and texture information; and generate, by a decoder, a modified image using the content embedding and the style embedding, wherein the modified image comprises the image content information of the first image data and the style information of the second image data.