Warped Perspective Correction
    12.
    发明公开

    公开(公告)号:US20240202866A1

    公开(公告)日:2024-06-20

    申请号:US18286522

    申请日:2022-03-29

    Applicant: Apple Inc.

    CPC classification number: G06T3/18 G02B27/017 G06T7/55

    Abstract: In one implementation, a method of performing perspective correction of an image is performed by a device including an image sensor, a display, one or more processors, and non-transitory memory. The method includes capturing, using the image sensor, an image of a physical environment. The method includes obtaining a plurality of initial depths respectively associated with a plurality of pixels of the image of the physical environment. The method includes generating a depth map for the image of the physical environment based on the plurality of initial depths and a respective plurality of confidences of the plurality of initial depths. The method includes transforming, using the one or more processors, the image of the physical environment based on the depth map and a difference between a perspective of the image sensor and a perspective of a user. The method includes displaying, on the display, the transformed image.

    Controlling an image sensor based on GPU temporal processing values

    公开(公告)号:US11736822B1

    公开(公告)日:2023-08-22

    申请号:US17176771

    申请日:2021-02-16

    Applicant: Apple Inc.

    CPC classification number: H04N5/351 G06T1/20 G06T1/60 H04N23/80

    Abstract: A method includes obtaining a first plurality of image frames that are provided by an image sensor at a first output rate. The method includes determining a GPU temporal processing value characterizing the GPU processing of the first plurality of image frames. The GPU temporal processing value is a function of an amount of information associated with the first plurality of image frames. The method includes determining an operation value associated with the image sensor based on a function of the GPU temporal processing value. The operation value modifies the operation of the image sensor. The method includes changing, using a controller, the operation of the image sensor as a function of the operation value so that the image sensor provides a second plurality of image frames at a second output rate.

    METHOD AND DEVICE FOR LATENCY REDUCTION OF AN IMAGE PROCESSING PIPELINE

    公开(公告)号:US20250156985A1

    公开(公告)日:2025-05-15

    申请号:US18922265

    申请日:2024-10-21

    Applicant: Apple Inc.

    Abstract: In some implementations, a method includes: determining a complexity value for first image data associated with of a physical environment that corresponds to a first time period; determining an estimated composite setup time based on the complexity value for the first image data and virtual content for compositing with the first image data; in accordance with a determination that the estimated composite setup time exceeds the threshold time: forgoing rendering the virtual content from the perspective that corresponds to the camera pose of the device relative to the physical environment during the first time period; and compositing a previous render of the virtual content for a previous time period with the first image data to generate the graphical environment for the first time period.

    Method and Device for Multi-Camera Hole Filling

    公开(公告)号:US20230377249A1

    公开(公告)日:2023-11-23

    申请号:US18089664

    申请日:2022-12-28

    Applicant: Apple Inc.

    Abstract: The method includes: obtaining a first image of an environment from a first image sensor associated with first intrinsic parameters; performing a warping operation on the first image according to perspective offset values to generate a warped first image in order to account for perspective differences between the first image sensor and a user of the electronic device; determining an occlusion mask based on the warped first image that includes a plurality of holes; obtaining a second image of the environment from a second image sensor associated with second intrinsic parameters; normalizing the second image based on a difference between the first and second intrinsic parameters to produce a normalized second image; and filling a first set of one or more holes of the occlusion mask based on the normalized second image to produce a modified first image.

    Automatically capturing a moment
    19.
    发明授权

    公开(公告)号:US11496723B1

    公开(公告)日:2022-11-08

    申请号:US16581074

    申请日:2019-09-24

    Applicant: Apple Inc.

    Abstract: Generating a representation of a scene includes detecting an indication to capture sensor data to generate a virtual representation of a scene in a physical environment at a first time, in response to the indication obtaining first sensor data from a first capture device at the first time, obtaining second sensor data from a second capture device at the first time, and combining the first sensor data and the second sensor data to generate the virtual representation of the scene.

Patent Agency Ranking