Patent №
US 9,934,553
Granted
2018-04-03
Filed 2016
Owner
THOMSON LICENSING
Lab
—
AI components
3
ml · vision · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
15341080
Image super-resolution (SR) generally enhance the resolution of images. One of SR's main challenge is discovering mappings between low-resolution (LR) and high-resolution (HR) image patches. The invention learns patch upscaling projection matrices from a training set of images. Input images are divided into overlapping patches, which are normalized and transformed to a defined orientation. Different transformations can be recognized and dealt with by using a simple 2D-projection. The transformed patches are clustered, and cluster specific upscaling projection matrices and corresponding cluster centroids determined during training are applied to obtain upscaled patches. The upscaled patches are assembled to an upscaled image.
AI classification
Ownership
THOMSON LICENSING
assignment · 440040633
Assignors
PEREZ PELLITERO, EDUARDO, SALVADOR MARCOS, JORDI, RUIZ HIDALGO, JAVIER, ROSENHAHN, BODO
On an employer assignment, the assignors are typically the inventors.