TRANSFORMING GRAYSCALE IMAGES INTO COLOR IMAGES USING DEEP NEURAL NETWORKS

Patent №

US 11,087,504

Granted

2021-08-10

Filed 2019

Owner

GOOGLE LLC

AI components

4

ml · vision · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16494386

Systems and methods for transforming grayscale images into color images using deep neural networks are described. One of the systems include one or more computers and one or more storage devices storing instructions that, when executed by one or more computers, cause the one or more computers to implement a coloring neural network, a refinement neural network, and a subsystem. The coloring neural network is configured to receive a first grayscale image having a first resolution and to process the first grayscale image to generate a first color image having a second resolution lower than the first resolution. The subsystem processes the first color image to generate a set of intermediate image outputs. The refinement neural network is configured to receive the set intermediate image outputs, and to process the set of intermediate image outputs to generate a second color image having a third resolution higher than the second resolution.

Machine learningVisionKnowledge representationAI hardwareG06T 11/001G06T 11/10G06T 3/40G06T 11/40G06T 2207/20081G06T 2207/20084

AI classification

Machine learning1.00
AI hardware1.00
Vision1.00
Knowledge representation0.95
Natural language0.24
Evolutionary computation0.00
Speech0.00
Planning0.00

Ownership

GOOGLE LLC

assignment · 504020177

Assignors

NOROUZI, MOHAMMAD, SHLENS, JONATHON, BIEBER, DAVID, COTADO, SERGIO GUADARRAMA, MURPHY, KEVIN PATRICK, DAHL, RYAN LIENHART

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

© 2026 NYSGPT2525 LLC