Image segmentation in virtual reality environments

    公开(公告)号:US10649614B2

    公开(公告)日:2020-05-12

    申请号:US15395564

    申请日:2016-12-30

    Applicant: Facebook, Inc.

    Abstract: In one embodiment, a method includes delineating a region in a two-dimensional (2D) image in a virtual reality environment, generating a mask based on an object detected in the delineated region, wherein the mask is defined by a perimeter, and generating a virtual object in the virtual reality environment, where the virtual object incorporates the detected object, and the virtual object is generated by applying the mask to a three-dimensional (3D) object. Delineating a region may include receiving user input that delineates the region, and the input may trace a perimeter of the region. Delineating a region may include detecting an object and determining a perimeter of the detected object. The detected object may be classified as corresponding to a specified object type. The 2D image may include a camera perspective view of an object in the virtual reality environment.

    SHARED THREE-DIMENSIONAL USER INTERFACE WITH PERSONAL SPACE

    公开(公告)号:US20200073534A1

    公开(公告)日:2020-03-05

    申请号:US16676810

    申请日:2019-11-07

    Applicant: Facebook, Inc.

    Abstract: Systems, methods, and non-transitory computer-readable media can present a shared three-dimensional computing environment to a plurality of users. A personal space associated with a current user is presented to the current user. The personal space comprises one or more content items visible only to the current user. A first content item is moved from the personal space to the shared three-dimensional computing environment. Moving the first content item from the personal space to the shared three-dimensional computing environment causes the first content item to be visible to the plurality of users.

    Image Segmentation in Virtual Reality Environments

    公开(公告)号:US20180188939A1

    公开(公告)日:2018-07-05

    申请号:US15395564

    申请日:2016-12-30

    Applicant: Facebook, Inc.

    Abstract: In one embodiment, a method includes delineating a region in a two-dimensional (2D) image in a virtual reality environment, generating a mask based on an object detected in the delineated region, wherein the mask is defined by a perimeter, and generating a virtual object in the virtual reality environment, where the virtual object incorporates the detected object, and the virtual object is generated by applying the mask to a three-dimensional (3D) object. Delineating a region may include receiving user input that delineates the region, and the input may trace a perimeter of the region. Delineating a region may include detecting an object and determining a perimeter of the detected object. The detected object may be classified as corresponding to a specified object type. The 2D image may include a camera perspective view of an object in the virtual reality environment.

    Shared three-dimensional user interface with personal space

    公开(公告)号:US11216152B2

    公开(公告)日:2022-01-04

    申请号:US16676810

    申请日:2019-11-07

    Applicant: Facebook, Inc.

    Abstract: Systems, methods, and non-transitory computer-readable media can present a shared three-dimensional computing environment to a plurality of users. A personal space associated with a current user is presented to the current user. The personal space comprises one or more content items visible only to the current user. A first content item is moved from the personal space to the shared three-dimensional computing environment. Moving the first content item from the personal space to the shared three-dimensional computing environment causes the first content item to be visible to the plurality of users.

    Picture-taking within virtual reality

    公开(公告)号:US10948993B2

    公开(公告)日:2021-03-16

    申请号:US16002365

    申请日:2018-06-07

    Applicant: Facebook, Inc.

    Abstract: In one embodiment, a method includes a computing system receiving hand configuration data associated with a user of an artificial reality application. The system may determine, based on the hand configuration data, that two fingers of a virtual left hand and two fingers of a virtual right hand of the user are extended. The system may determine that those fingers define a quadrilateral in a virtual environment, with the two fingers of the virtual left hand defining a first corner of the quadrilateral and the two fingers of the virtual right hand defining an opposite corner of the quadrilateral. The system may generate, based on the quadrilateral and a viewpoint of the user in the virtual environment, an image that captures a scene in the virtual environment. The system may then display the generated image in the virtual environment.

Patent Agency Ranking