Super-resolution apparatus and method for virtual and mixed reality
AssigneeIntel Corporation
InventorsZhengmin LI, Atsuo KUWAHARA, Deepak VEMBAR
Life of this patent
Estimating the term…
Abstract
An apparatus and method for efficiently improving virtual/real interactions in augmented reality. For example, one embodiment of a method comprises: capturing a raw image including depth data; identifying one or more regions of interest based on a detected spatial proximity of one or more virtual objects and one or more real objects; generating a super-resolution map of the one or more regions of interest using machine-learning techniques or results thereof; detecting interactions between the virtual objects and the real objects using the super-resolution map; and performing one or more graphics processing or general purpose processing operations based on the detected interactions.
Claims21
(canceled)
A processor comprising:
- first circuitry to identify a region of interest based on spatial proximity between one or more virtual objects and real objects, wherein spatial proximity between a virtual object and a real object is determined based on distance measurements between a user and the virtual object, and between the user and the real object;
- and
- second circuitry to generate a map of the region of interest using machine learning, wherein interactions between the virtual object and real object is detected based on the map.
A method comprising:
- identifying a region of interest based on spatial proximity between one or more virtual objects and real objects, wherein spatial proximity between a virtual object and a real object based on distance measurements between a user and the virtual object, and between the user and the real object;
- generating a map of the region of interest using machine learning;
- and
- detecting interactions between the virtual object and real object is detected based on the map.
A non-transitory machine-readable storage medium having program code stored therein which, when executed by a machine, is capable of causing the machine to perform:
- identifying a region of interest based on spatial proximity between one or more virtual objects and real objects, wherein spatial proximity between a virtual object and a real object based on distance measurements between a user and the virtual object, and between the user and the real object;
- generating a map of the region of interest using machine learning;
- and
- detecting interactions between the virtual object and real object is detected based on the map.
Dependencies are inferred from the claim text.