-
公开(公告)号：US20200184602A1
公开(公告)日：2020-06-11
申请号：US16685348
申请日：2019-11-15
Applicant: INTEL CORPORATION
Inventor： Zhengmin LI , Atsuo KUWAHARA , Deepak VEMBAR
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.
-
公开(公告)号：US20240323341A1
公开(公告)日：2024-09-26
申请号：US18126403
申请日：2023-03-25
Applicant: Intel Corporation
Inventor： Oliver GRAU , Deepak VEMBAR
IPC: H04N13/344 , H04N13/156 , H04N13/383
CPC classification number: H04N13/344 , H04N13/156 , H04N13/383
Abstract: A system and method for foveated stereo rendering. For example, one embodiment of an apparatus comprises: a graphics processor comprising graphics processing circuitry to render images of a graphics scene to be displayed in a head mounted display (HMD); and an interface to couple the graphics processing circuitry to the HMD, wherein to render the images, the graphics processing circuitry is to perform operations comprising: rendering a peripheral image having a first resolution based on a first viewpoint of the graphics scene, rendering first and second foveal regions of the graphics scene at a second resolution higher than the first resolution, wherein the first foveal region is based on a second viewpoint of the graphics scene corresponding to the first HMD display, and the second foveal region is based on a third viewpoint of the graphics scene corresponding to the second HMD display, and blending the first foveal region with the peripheral image to render a first final image to be displayed on the first HMD display, and blending the second foveal region with the peripheral image to render a second final image to be displayed on the second HMD display.
-
公开(公告)号：US20220092741A1
公开(公告)日：2022-03-24
申请号：US17487882
申请日：2021-09-28
Applicant: INTEL CORPORATION
Inventor： Zhengmin LI , Atsuo KUWAHARA , Deepak VEMBAR
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.
-
-
Search Results
3
records
(took 0.012 seconds)
