Super resolution using fidelity transfer
AssigneeMagic Pony Technology Limited
InventorsZehan Wang, Robert David Bishop, Lucas Theis
Life of this patent
Estimating the term…
Abstract
Systems and methods for developing improved-fidelity visual data using fidelity data and using a hierarchical algorithm are provided. An example method includes receiving at least a plurality of neighbouring sections of visual data, selecting a plurality of input sections from the received plurality of neighbouring sections of visual data, extracting features from the plurality of input sections of visual data, and producing the improved-fidelity visual data by applying the fidelity data to the extracted features.
Claims20
A method for developing improved-fidelity visual data using fidelity data and using a hierarchical algorithm, the method comprising the steps of:
- receiving at least a plurality of neighbouring sections of visual data;
- selecting a plurality of input sections from the received plurality of neighbouring sections of visual data;
- extracting features from the plurality of input sections of visual data;
- and
- producing the improved-fidelity visual data by applying the fidelity data to the extracted features.
An Apparatus comprising:
- at least one processor;
- and
- at least one memory including computer program code which, when executed by the at least one processor, causes the apparatus to:
- receive at least a plurality of neighbouring sections of visual data;
- select a plurality of input sections from the received plurality of neighbouring sections of visual data;
- extract features from the plurality of input sections of visual data;
- and
- produce improved-fidelity visual data by applying fidelity data to the extracted features.
A computer-readable medium having computer-readable code stored thereon, the computer-readable code, when executed by at least one processor, causing the processor to:
- receive at least a plurality of neighbouring sections of visual data;
- select a plurality of input sections from the received plurality of neighbouring sections of visual data;
- extract features from the plurality of input sections of visual data;
- and
- produce improved-fidelity visual data by applying fidelity data to the extracted features.
Dependencies are inferred from the claim text.