公开(公告)号：US11922636B2

公开(公告)日：2024-03-05

申请号：US17283688

申请日：2019-10-09

Applicant: GOOGLE LLC

Inventor： David Bond ,  Mark Dochtermann

IPC: G06T7/20 ,  G01P15/00 ,  G06T7/194 ,  G06T7/70 ,  G06T11/00 ,  G06T19/00 ,  G06V40/16

CPC classification number: G06T7/20 ,  G01P15/00 ,  G06T7/194 ,  G06T7/70 ,  G06T11/00 ,  G06T19/006 ,  G06V40/16

Abstract: An electronic device places an augmented reality object in an image of a real environment based on a pose of the electronic device and based on image segmentation. The electronic device includes a camera that captures images of the real environment and sensors, such as an inertial measurement unit (IMU), that capture a pose of the electronic device. The electronic device selects an augmented reality (AR) object from a memory, segments a captured image of the real environment into foreground pixels and background pixels, and composites an image for display wherein the AR object is placed between the foreground pixels and the background pixels. As the pose of the electronic device changes, the electronic device maintains the relative position of the AR object with respect to the real environment in images for display.

公开(公告)号：US20240185525A1

公开(公告)日：2024-06-06

申请号：US18074860

申请日：2022-12-05

Applicant: Google LLC

Inventor： Bryan Landsiedel ,  Topraj Gurung ,  Tianyu Liang ,  Sergey Milenkiy ,  Peter Kammer ,  Paul Byrne ,  Lance Engle ,  James Beattie ,  Ehsan Barekati ,  David Bond ,  David Black ,  Bryan Woods ,  Bret Stastny ,  Benjamin Molyneaux ,  Jeremy Swanson ,  Timothy Jones

IPC: G06T17/20 ,  G06F9/50

CPC classification number: G06T17/20 ,  G06F9/505

Abstract: A system and method of managing a model, such as a digital twin. The method may involve receiving three-dimensional model data representative of a setting, converting the three-dimensional model data into a simplified model using a parallel processing pipeline architecture, rendering the simplified model using a three-dimensional model rendering platform, converting a view of the rendered model from a specific position at a specific angle into a streamable format, and transmitting the streamable format of the view of the rendered model to an end-user terminal over a network connection.