Loading patent…
AssigneeMagic Pony Technology Limited
InventorsZehan Wang, Wenzhe Shi, Ferenc Huszar, Robert David Bishop
Estimating the term…
A method for training an algorithm to process at least a section of received visual data using a training dataset and reference dataset. The method comprises an iterative method with iterations comprising: generating a set of training data using the algorithm; comparing one or more characteristics of the training data to one or more characteristics of at least a section of the reference dataset; and modifying one or more parameters of the algorithm to optimise processed visual data based on the comparison between the characteristic of the training data and the characteristic of the reference dataset. The algorithm may output the processed visual data with the same content as the at least a section of received visual data. Some aspects and/or implementations provide for improved super-resolution of lower quality images to produce super-resolution images with improved characteristics (e.g. less blur, less undesired smoothing) compared to other super-resolution techniques.
A method for training an algorithm to process at least a section of received visual data using a training dataset and reference dataset, the method being an iterative method with each iteration comprising:
An apparatus comprising:
A computer-readable medium having computer-readable code stored thereon, the computer-readable code, when executed by at least one processor, cause the processor to perform an iterative method, wherein to perform an iteration of the iterative method, the instructions cause the processor to:
Dependencies are inferred from the claim text.