IMAGE MANIPULATION USING DEEP LEARNING TECHNIQUES IN A PATCH MATCHING OPERATION

Patent №

US 11,080,833

Granted

2021-08-03

Filed 2019

Owner

ADOBE INC.

Lab

AI components

7

ml · nlp · vision · kr · planning · evo · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16692843

A method for manipulating a target image includes generating a query of the target image and keys and values of a first reference image. The method also includes generating matching costs by comparing the query of the target image with each key of the reference image and generating a set of weights from the matching costs. Further, the method includes generating a set of weighted values by applying each weight of the set of weights to a corresponding value of the values of the reference image and generating a weighted patch by adding each weighted value of the set of weighted values together. Additionally, the method includes generating a combined weighted patch by combining the weighted patch with additional weighted patches associated with additional queries of the target image and generating a manipulated image by applying the combined weighted patch to an image processing algorithm.

Machine learningNatural languageVisionKnowledge representationPlanningEvolutionary computationAI hardwareG06N 3/045G06F 16/53G06F 18/22G06N 3/0464G06N 3/08G06N 3/09G06T 5/50G06T 5/70+7 more

AI classification

Vision1.00
Machine learning1.00
Planning0.98
AI hardware0.98
Knowledge representation0.95
Evolutionary computation0.63
Natural language0.53
Speech0.00

Ownership

ADOBE INC.

assignment · 540530143

Assignors

BARNES, CONNELLY, SINGHAL, UTKARSH, SHECHTMAN, ELYA, GHARBI, MICHAEL

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC