VIDEO PRESENTATION SYSTEM
    121.
    发明公开

    公开(公告)号:US20240323318A1

    公开(公告)日:2024-09-26

    申请号:US18188845

    申请日:2023-03-23

    IPC分类号: H04N7/15 G06V20/40 G10L15/18

    摘要: A computer hardware system includes a video analyzer configured to assist in a presentation of at least a portion of a video to a plurality of participants by a presenter on a presenter client and a hardware processor configured to perform the following executable operations. The video is analyzed to generate a plurality of segments. Presenter data is captured during the presentation, and presenter intent is determined based upon the presenter data. Based upon the presenter intent, forward-looking controls are presented only to the presenter client. One of the plurality of segments is identified using at least one of the presenter intent and the forward-looking controls. The identified one segment is presented to the plurality of participants.

    RECORDING SELECTIVE METAVERSE COLLABORATION CONTENT

    公开(公告)号:US20240323236A1

    公开(公告)日:2024-09-26

    申请号:US18123419

    申请日:2023-03-20

    IPC分类号: H04L65/1066 G06Q10/101

    CPC分类号: H04L65/1066 G06Q10/101

    摘要: A computer-implemented method, system and computer program product for selectively recording metaverse collaboration content. Contextual boundaries to perform selective recording in a collaborative environment of a metaverse are received from a user. Contextual boundaries refer to designations in the collaborative environment, including participants and collaboration content being shared, based on the context of the collaborative environment. In addition to receiving contextual boundaries, a workflow sequence, which defines portions of the contextual boundaries to record, is received from the user. A workflow sequence refers to the order of the selective recording in the collaborative environment of the metaverse. Metaverse collaboration content in the collaborative environment is then recorded using a recording node sequence based on the workflow sequence. A second collaborative environment of the metaverse may then be created based on the recorded metaverse collaboration content. In this manner, user-designated metaverse collaboration content in the metaverse may be selectively recorded.

    AUGMENTED REALITY ENVIRONMENT MELDING
    128.
    发明公开

    公开(公告)号:US20240320928A1

    公开(公告)日:2024-09-26

    申请号:US18188600

    申请日:2023-03-23

    IPC分类号: G06T19/00 G06T19/20

    CPC分类号: G06T19/006 G06T19/20

    摘要: Techniques are described with respect to a system, method, and computer program product for merging augmented reality experiences into an augmented reality environment. An associated method includes determining a first augmented reality experience of a first user and a second augmented reality experience of a second user; analyzing a plurality of environmental contextual data associated with the first augmented reality experience and the second augmented reality experience; and based on the analysis, generating a merged augmented reality environment comprising the first user and the second user.

    MIXED REALITY AVATAR EYE INPAINTING BASED ON USER SPEECH

    公开(公告)号:US20240320926A1

    公开(公告)日:2024-09-26

    申请号:US18187328

    申请日:2023-03-21

    IPC分类号: G06T19/00 G06T17/20

    摘要: According to one embodiment, a method, computer system, and computer program product for mixed reality is provided. The present invention may include receiving one or more 3D non-eye landmarks of a user; receiving at least one voice audio of the user; using random noise sampled with a unit normal distribution as one or more noised 3D eye landmarks for the user; inputting the received one or more 3D non-eye landmarks of the user, the at least one voice audio of the user, and the one or more noised 3D eye landmarks for the user, into a trained eye landmark generative model; generating one or more 3D eye landmarks for the user using the trained eye landmark generative model; performing iterative refinement of the one or more generated 3D eye landmarks using the trained eye landmark generative model; and rendering the user's generated face model using a formed 3D face mesh.