DYNAMICALLY GENERATED INTERFACE TRANSITIONS

    公开(公告)号:US20230116393A1

    公开(公告)日:2023-04-13

    申请号:US18079699

    申请日:2022-12-12

    Applicant: Google LLC

    Abstract: Techniques are described for determining a duration for a transition and alteration of the appearance of a user interface (UI) from a first UI state to a second UI state over the transition duration according to a timing function that specifies different rates of change in appearance over the course of the transition and is derived by adjusting a master timing function that is used to control a plurality of transitions in the UI to span the transition duration for the transition. A time value of an inflection point within the timing function is determined and the transition duration is divided into a first portion and a second portion so that the first portion extends from the beginning of the transition duration to the time value of the inflection point, and the second portion extends from the time value of the inflection point to the end of the transition duration.

    Few-shot synthesis of talking heads

    公开(公告)号:US12026833B2

    公开(公告)日:2024-07-02

    申请号:US17310678

    申请日:2020-10-28

    Applicant: Google LLC

    Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

    Dynamically generated interface transitions

    公开(公告)号:US12020005B2

    公开(公告)日:2024-06-25

    申请号:US18079699

    申请日:2022-12-12

    Applicant: Google LLC

    CPC classification number: G06F8/38 G06F3/048 G06T13/80

    Abstract: Techniques are described for determining a duration for a transition and alteration of the appearance of a user interface (UI) from a first UI state to a second UI state over the transition duration according to a timing function that specifies different rates of change in appearance over the course of the transition and is derived by adjusting a master timing function that is used to control a plurality of transitions in the UI to span the transition duration for the transition. A time value of an inflection point within the timing function is determined and the transition duration is divided into a first portion and a second portion so that the first portion extends from the beginning of the transition duration to the time value of the inflection point, and the second portion extends from the time value of the inflection point to the end of the transition duration.

    FEW-SHOT SYNTHESIS OF TALKING HEADS

    公开(公告)号:US20220130111A1

    公开(公告)日:2022-04-28

    申请号:US17310678

    申请日:2020-10-28

    Applicant: Google LLC

    Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

    Dynamically generated interface transitions

    公开(公告)号:US11544043B2

    公开(公告)日:2023-01-03

    申请号:US16475325

    申请日:2018-08-21

    Applicant: Google LLC

    Abstract: Techniques are described for determining a duration for a transition and alteration of the appearance of a user interface (UI) from a first UI state to a second UI state over the transition duration according to a timing function that specifies different rates of change in appearance over the course of the transition and is derived by adjusting a master timing function that is used to control a plurality of transitions in the UI to span the transition duration for the transition. A time value of an inflection point within the timing function is determined and the transition duration is divided into a first portion and a second portion so that the first portion extends from the beginning of the transition duration to the time value of the inflection point, and the second portion extends from the time value of the inflection point to the end of the transition duration.

Patent Agency Ranking