IMAGE SUPER RESOLUTION VIA SPARE REPRESENTATION OF MULTI-CLASS SEQUENTIAL AND JOINT DICTIONARIES

Patent №

US 9,865,036

Granted

2018-01-09

Filed 2015

Owner

PIXELWORKS, INC.

Lab

AI components

2

ml · vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

14615075

A method of developing an image training library includes receiving, at a processor, a set of high resolution image samples at a first resolution, generating a set of low resolution image samples having a second resolution from the set of high resolution images, wherein the second resolution is lower than the first resolution, clustering the low resolution image samples using features in the low resolution images, generating a low resolution dictionary for each cluster, generating sparse coefficients for each sample, and using the sparse coefficients to generate a high resolution dictionary for each cluster.

Machine learningVisionG06T 3/4053G06F 18/214G06F 18/23

AI classification

Vision1.00
Machine learning1.00
Knowledge representation0.47
Natural language0.33
AI hardware0.29
Planning0.00
Speech0.00
Evolutionary computation0.00

Ownership

PIXELWORKS, INC.

assignment · 348990687

Assignors

LIU, GUODONG, CHEN, JUNHUA, WOODALL, NEIL, MA, YUE, ZHANG, BOB

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

© 2026 NYSGPT2525 LLC