Machine learning-based multi-view video conferencing from single view video data
AssigneeAdvanced Micro Devices, Inc.
InventorRoto Le
Life of this patent
Estimating the term…
Abstract
Machine learning-based multi-view video conferencing from single view video data, including: identifying, in video data, a plurality of objects; and generating a user interface comprising a plurality of first user interface elements each comprising a portion of the video data corresponding to one or more of the plurality of objects.
Claims20
A method for machine learning-based multi-view video conferencing from single view video data, the method comprising:
- identifying, in video data, a plurality of objects;
- and
- generating a user interface comprising a plurality of first user interface elements each comprising a portion of the video data corresponding to one or more of the plurality of objects, wherein the user interface includes a grouping of two or more of the plurality of objects into a same user interface element of the plurality of first user interface elements based on a relationship between the two or more of the plurality of objects.
An apparatus for machine learning-based multi-view video conferencing from single view video data, the apparatus comprising a computer processor and a computer memory, the computer memory including computer program instructions that, when executed by the computer processor, cause the computer processor to carry out:
- identifying, in video data, a plurality of objects;
- and
- generating a user interface comprising a plurality of first user interface elements each comprising a portion of the video data corresponding to one or more of the plurality of objects, wherein the user interface includes a grouping of two or more of the plurality of objects into a same user interface element of the plurality of first user interface elements based on a relationship between the two or more of the plurality of objects.
A computer program product disposed upon a non-transitory computer readable medium, the computer program product comprising computer program instructions for machine learning-based multi-view video conferencing from single view video data that, when executed, cause a computer system to perform steps comprising:
- identifying, in video data, a plurality of objects;
- and
- generating a user interface comprising a plurality of first user interface elements each comprising a portion of the video data corresponding to one or more of the plurality of objects, wherein the user interface includes a grouping of two or more of the plurality of objects into a same user interface element of the plurality of first user interface elements based on a relationship between the two or more of the plurality of objects.
Dependencies are inferred from the claim text.