Real-time augmented reality item guide
AssigneeeBay Inc.
InventorTsun Kwan Donald Siu
Life of this patent
Estimating the term…
Abstract
A real-time augmented reality item guide is described. A service platform may receive a digital image depicting at least one item. A plurality of listings for the at least one item on the service platform is identified via at least one machine learning model of the service platform based on the digital image, each of the plurality of listings associated with a respective point in time. An aspect is fetched from each of the plurality of listings for the at least one item on the service platform. Time-dependent augmented reality digital content is generated for the at least one item based on the aspect. The time-dependent augmented reality digital content is rendered as an overlay on the digital image.
Claims20
A method for an augmented reality guide, the method comprising:
- receiving, by a service platform, a digital image of a plurality of digital images comprising a live stream, the digital image depicting at least one item;
- identifying, via at least one machine learning model of the service platform, a plurality of listings for the at least one item on the service platform by:
- detecting a boundary of the at least one item based on the digital image;
- outputting feature vectors corresponding to at least a portion of the digital image within the boundary;
- and
- matching the feature vectors to the at least one item in the plurality of listings, wherein the plurality of listings is associated with respective points in time;
- fetching at least one respective aspect from the plurality of listings for the at least one item on the service platform;
- generating time-dependent augmented reality digital content for the at least one item based on the at least one respective aspect;
- receiving data from one or more orientation sensors, wherein the data corresponds to a view of the at least one item in the live stream of the plurality of digital images;
- and
- rendering, for display via a user interface and based on the data, the time-dependent augmented reality digital content as an overlay on the live stream, wherein the time-dependent augmented reality digital content remains as is relative to the view of the at least one item in the live stream of the plurality of digital images.
A computing device comprising:
- a processing system;
- and
- a computer-readable storage medium storing instructions that, responsive to execution by the processing system, causes the processing system to perform operations comprising:
- receiving, by a service platform, a digital image of a plurality of digital images comprising a live stream, the digital image depicting at least one item;
- identifying, via at least one machine learning model of the service platform, a plurality of listings for the at least one item on the service platform by:
- detecting a boundary of the at least one item based on the digital image;
- outputting feature vectors corresponding to at least a portion of the digital image within the boundary;
- and
- matching the feature vectors to the at least one item in the plurality of listings, wherein the plurality of listings is associated with respective points in time;
- fetching at least one respective aspect from the plurality of listings for the at least one item on the service platform;
- generating time-dependent augmented reality digital content for the at least one item based on the at least one respective aspect;
- receiving data from one or more orientation sensors, wherein the data corresponds to a view of the at least one item in the live stream of the plurality of digital images;
- and
- rendering, for display via a user interface and based on the data, the time-dependent augmented reality digital content as an overlay on the live stream, wherein the time-dependent augmented reality digital content remains as is relative to the view of the at least one item in the live stream of the plurality of digital images.
A computer-readable storage medium storing instructions that, responsive to execution by one or more processors, causes the one or more processors to perform operations comprising:
- receiving, by a service platform, a digital image of a plurality of digital images comprising a live stream, the digital image depicting at least one item;
- identifying, via at least one machine learning model of the service platform, a plurality of listings for the at least one item on the service platform by:
- detecting a boundary of the at least one item based on the digital image;
- outputting feature vectors corresponding to at least a portion of the digital image within the boundary;
- and
- matching the feature vectors to the at least one item in the plurality of listings, wherein the plurality of listings is associated with respective points in time;
- fetching at least one respective aspect from the plurality of listings for the at least one item on the service platform;
- generating time-dependent augmented reality digital content for the at least one item based on the at least one respective aspect;
- receiving data from one or more orientation sensors, wherein the data corresponds to a view of the at least one item in the live stream of the plurality of digital images;
- and
- rendering, for display via a user interface and based on the data, the time-dependent augmented reality digital content as an overlay on the live stream, wherein the time-dependent augmented reality digital content remains as is relative to the view of the at least one item in the live stream of the plurality of digital images.
Dependencies are inferred from the claim text.