Systems and methods for increasing resolution of video data
AssigneeFacebook, Inc.
InventorDouglas Michael Mayle
Life of this patent
Estimating the term…
Abstract
Systems, methods, and non-transitory computer readable media can obtain a first plurality of frames of a video having a first resolution. For each frame of the first plurality of frames, a portion of a corresponding frame of a version of the video having a second resolution that is higher than the first resolution can be sampled to generate a bias for the frame. A second plurality of frames of the video including the respective bias can be generated, wherein the second plurality of frames corresponds to the first plurality of frames. A second plurality of frames of the video including the respective bias can be generated.
Claims20
A computer-implemented method comprising:
- obtaining, by a computing system, a first plurality of frames of a video having a first resolution;
- sampling, by the computing system, for each frame of the first plurality of frames, a portion of a corresponding frame of a version of the video having a second resolution that is higher than the first resolution to generate a bias for the frame;
- generating, by the computing system, a second plurality of frames of the video including the respective bias, wherein the second plurality of frames corresponds to the first plurality of frames;
- and
- generating, by the computing system, a bias series indicating a location of the bias in each frame of the second plurality of frames.
A system comprising:
- at least one hardware processor;
- and
- a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
- obtaining a first plurality of frames of a video having a first resolution;
- sampling, for each frame of the first plurality of frames, a portion of a corresponding frame of a version of the video having a second resolution that is higher than the first resolution to generate a bias for the frame;
- generating a second plurality of frames of the video including the respective bias, wherein the second plurality of frames corresponds to the first plurality of frames;
- and
- generating a bias series indicating a location of the bias in each frame of the second plurality of frames.
A non-transitory computer readable medium including instructions that, when executed by at least one hardware processor of a computing system, cause the computing system to perform a method comprising:
- obtaining a first plurality of frames of a video having a first resolution;
- sampling, for each frame of the first plurality of frames, a portion of a corresponding frame of a version of the video having a second resolution that is higher than the first resolution to generate a bias for the frame;
- generating a second plurality of frames of the video including the respective bias, wherein the second plurality of frames corresponds to the first plurality of frames;
- and
- generating a bias series indicating a location of the bias in each frame of the second plurality of frames.
Dependencies are inferred from the claim text.