UTILIZING AN OBJECT RELIGHTING NEURAL NETWORK TO GENERATE DIGITAL IMAGES ILLUMINATED FROM A TARGET LIGHTING DIRECTION

Patent №

US 10,692,276

Granted

2020-06-23

Filed 2018

Owner

ADOBE SYSTEMS INCORPORATED

Lab

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15970367

The present disclosure relates to using an object relighting neural network to generate digital images portraying objects under target lighting directions based on sets of digital images portraying the objects under other lighting directions. For example, in one or more embodiments, the disclosed systems provide a sparse set of input digital images and a target lighting direction to an object relighting neural network. The disclosed systems then utilize the object relighting neural network to generate a target digital image that portrays the object illuminated by the target lighting direction. Using a plurality of target digital images, each portraying a different target lighting direction, the disclosed systems can also generate a modified digital image portraying the object illuminated by a target lighting configuration that comprises a combination of the different target lighting directions.

Machine learningVisionAI hardwareG06T 15/506G06N 3/045G06N 3/0455G06N 3/0464G06N 3/08G06N 3/09G06N 20/00G06T 7/70+2 more

AI classification

Vision1.00
Machine learning1.00
AI hardware0.73
Knowledge representation0.50
Planning0.45
Evolutionary computation0.00
Natural language0.00
Speech0.00

Ownership

ADOBE SYSTEMS INCORPORATED

assignment · 457090332

Assignors

SUNKAVALLI, KALYAN, XU, ZEXIANG, HADAP, SUNIL

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

From the same owner

© 2026 NYSGPT2525 LLC