Back to results
US 10,339,716 B1Granted
System and method for dense, large scale scene reconstruction
AssigneeOccipital, Inc.
InventorsJeffrey Powers, Nicolas Burrus, Yuping Lin, Paul Schroeder
Life of this patent
Estimating the term…
Abstract
A system configured to improve the operations associated with generating virtual representations on limited resources of a mobile device. In some cases, the system may utilize viewpoint bundles that include collection of image data with an associated pose in relative physical proximity to each other to render a virtual scene. In other cases, the system may utilize 2.5D manifolds including 2D image data and a weighted depth value to render the 3D environment.
Claims20
A system comprising:
- a display for presenting a virtual environment to a user;
- one or more image components for capturing image data associated with a physical environment surrounding the user;
- one or more processors;
- non-transitory computer-readable media storing computer-executable instructions, which when executed by the one or more processors cause the one or more processors to perform operations including:
- receiving first image data captured by the one or more image components at a first time;
- organizing the first image data into a first viewpoint based at least in part on a first pose associated with the system at the first time;
- assigning the first viewpoint to a first viewpoint bundle;
- integrating the first image data into a Truncated Signed Distance Function (TSDF);
- receiving second image data from the one or more image components, the second image data captured at a second time, the second time after the first time;
- organizing the second image data into a second viewpoint based at least in part on a second pose associated with the system at the second time;
- determining the second pose is greater than a threshold distance from a first viewpoint bundle pose associated with the first viewpoint bundle;
- generating a second viewpoint bundle based at least in part on the second viewpoint;
- assigning the second viewpoint bundle a second viewpoint pose based at least in part on the second pose associated with the system at the second time;
- and
- integrating the second image data into the TSDF.
12 more elements
A method comprising:
- receiving first image data captured by the one or more image components at a first time;
- organizing the first image data into a first viewpoint based at least in part on a first pose associated with the system at the first time;
- assigning the first viewpoint to a first viewpoint bundle;
- integrating the first image data into a Truncated Signed Distance Function (TSDF);
- receiving second image data from the one or more image components, the second image data captured at a second time, the second time after the first time;
- organizing the second image data into a second viewpoint based at least in part on a second pose associated with the system at the second time;
- determining the second pose is greater than a threshold distance from a first viewpoint bundle pose associated with the first viewpoint bundle;
- generating a second viewpoint bundle based at least in part on the second viewpoint;
- assigning the second viewpoint bundle a second viewpoint pose based at least in part on the second pose associated with the system at the second time;
- and
- integrating the second image data into the TSDF.
8 more elements
A non-transitory computer-readable media storing computer-executable instructions, which when executed by one or more processors cause the one or more processors to perform operations including:
- receiving first image data captured by the one or more image components at a first time;
- organizing the first image data into a first viewpoint based at least in part on a first pose associated with the system at the first time;
- assigning the first viewpoint to a first viewpoint bundle;
- integrating the first image data into a Truncated Signed Distance Function (TSDF);
- receiving second image data from the one or more image components, the second image data captured at a second time, the second time after the first time;
- organizing the second image data into a second viewpoint based at least in part on a second pose associated with the system at the second time;
- determining the second pose is greater than a threshold distance from a first viewpoint bundle pose associated with the first viewpoint bundle;
- generating a second viewpoint bundle based at least in part on the second viewpoint;
- assigning the second viewpoint bundle a second viewpoint pose based at least in part on the second pose associated with the system at the second time;
- and
- integrating the second image data into the TSDF.
8 more elements
Dependencies are inferred from the claim text.