Frame-recurrent video super-resolution

    公开(公告)号:US10783611B2

    公开(公告)日:2020-09-22

    申请号:US15859992

    申请日:2018-01-02

    Applicant: Google LLC

    Abstract: The present disclosure provides systems and methods to increase resolution of imagery. In one example embodiment, a computer-implemented method includes obtaining a current low-resolution image frame. The method includes obtaining a previous estimated high-resolution image frame, the previous estimated high-resolution frame being a high-resolution estimate of a previous low-resolution image frame. The method includes warping the previous estimated high-resolution image frame based on the current low-resolution image frame. The method includes inputting the warped previous estimated high-resolution image frame and the current low-resolution image frame into a machine-learned frame estimation model. The method includes receiving a current estimated high-resolution image frame as an output of the machine-learned frame estimation model, the current estimated high-resolution image frame being a high-resolution estimate of the current low-resolution image frame.

    Compact Language-Free Facial Expression Embedding and Novel Triplet Training Scheme

    公开(公告)号:US20200151438A1

    公开(公告)日:2020-05-14

    申请号:US16743439

    申请日:2020-01-15

    Applicant: Google LLC

    Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a facial expression model that is configured to provide a facial expression embedding. In particular, the facial expression model can receive an input image that depicts a face and, in response, provide a facial expression embedding that encodes information descriptive of a facial expression made by the face depicted in the input image. As an example, the facial expression model can be or include a neural network such as a convolutional neural network. The present disclosure also provides a novel and unique triplet training scheme which does not rely upon designation of a particular image as an anchor or reference image.

    Frame-Recurrent Video Super-Resolution
    3.
    发明申请

    公开(公告)号:US20190206026A1

    公开(公告)日:2019-07-04

    申请号:US15859992

    申请日:2018-01-02

    Applicant: Google LLC

    Abstract: The present disclosure provides systems and methods to increase resolution of imagery. In one example embodiment, a computer-implemented method includes obtaining a current low-resolution image frame. The method includes obtaining a previous estimated high-resolution image frame, the previous estimated high-resolution frame being a high-resolution estimate of a previous low-resolution image frame. The method includes warping the previous estimated high-resolution image frame based on the current low-resolution image frame. The method includes inputting the warped previous estimated high-resolution image frame and the current low-resolution image frame into a machine-learned frame estimation model. The method includes receiving a current estimated high-resolution image frame as an output of the machine-learned frame estimation model, the current estimated high-resolution image frame being a high-resolution estimate of the current low-resolution image frame.

    Modeling Dependencies with Global Self-Attention Neural Networks

    公开(公告)号:US20230359865A1

    公开(公告)日:2023-11-09

    申请号:US18044842

    申请日:2020-09-16

    Applicant: Google LLC

    CPC classification number: G06N3/045 G06N3/084

    Abstract: The present disclosure provides systems, methods, and computer program products for modeling dependencies throughout a network using a global-self attention model with a content attention layer and a positional attention layer that operate in parallel. The model receives input data comprising content values and context positions. The content attention layer generates one or more output features for each context position based on a global attention operation applied to the content values independent of the context positions. The positional attention layer generates an attention map for each of the context positions based on one or more content values of the respective context position and associated neighboring positions. Output is determined based on the output features generated by the content attention layer and the attention map generated for each context position by the positional attention layer. The model improves efficiency and can be used throughout a deep network.

    Compact language-free facial expression embedding and novel triplet training scheme

    公开(公告)号:US11163987B2

    公开(公告)日:2021-11-02

    申请号:US16743439

    申请日:2020-01-15

    Applicant: Google LLC

    Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a facial expression model that is configured to provide a facial expression embedding. In particular, the facial expression model can receive an input image that depicts a face and, in response, provide a facial expression embedding that encodes information descriptive of a facial expression made by the face depicted in the input image. As an example, the facial expression model can be or include a neural network such as a convolutional neural network. The present disclosure also provides a novel and unique triplet training scheme which does not rely upon designation of a particular image as an anchor or reference image.

Patent Agency Ranking