公开(公告)号：US20230230325A1

公开(公告)日：2023-07-20

申请号：US18001881

申请日：2021-06-18

Applicant: Google LLC

Inventor： Shengyi Lin ,  Leslie Tsu-Hwa Shaw ,  Marius Renn ,  Nisha Masharani ,  Sushil Nath

IPC: G06T19/00 ,  G06V40/16 ,  H04N23/63

CPC classification number: G06T19/00 ,  G06V40/172 ,  G06V40/168 ,  H04N23/632 ,  G06T2200/24

Abstract: An example method includes outputting, by a computing device for display, one or more digital images that include a face of a user, receiving, by the computing device and based on a facial recognition process, an indication of a match between facial data associated with the face of the user and reference facial data associated with a face of an enrolled user of the computing device, and retrieving, by the computing device, digital makeup enhancement data that is associated with the reference facial data. The example method further includes applying, by the computing device, the digital makeup enhancement data to the facial data, of tire face of the user to generate one or more modified digital images that indicate at least one corresponding digital makeup enhancement to the face of the user, and outputting, by the computing device for display, the one or more modified digital images.

公开(公告)号：US10547790B2

公开(公告)日：2020-01-28

申请号：US16008697

申请日：2018-06-14

Applicant: Google LLC

Inventor： Radford Juang ,  Chia-Kai Liang ,  Wei Hong ,  Senpo Hu ,  Shengyi Lin ,  Erik Gross

IPC: H04N5/232

Abstract: Implementations generally relate to locking a camera onto a sub-region to capture images of the sub-region with a moving camera. In some implementations, a method includes determining a first region in a scene detected by a camera while the camera is in a first physical position. The method further includes receiving user input to target a sub-region within the first capture region of the scene and capturing the first image of the sub-region while the camera is in the first physical position. The first image is displayed in a fixed orientation on a preview portion of a display screen. The camera is moved to a second physical position and a second capture region of the scene is detected. The method further includes capturing a second image is of the sub-region and displaying it in the fixed orientation on the preview portion of the display screen. The second image is effective to inform a user of whether capture of the sub-region is altered by camera movement.

公开(公告)号：US20190387171A1

公开(公告)日：2019-12-19

申请号：US16008697

申请日：2018-06-14

Applicant: Google LLC

Inventor： Radford Juang ,  Chia-Kai Liang ,  Wei Hong ,  Senpo Hu ,  Shengyi Lin ,  Erik Gross

IPC: H04N5/232

Abstract: Implementations generally relate to locking a camera onto a sub-region to capture images of the sub-region with a moving camera. In some implementations, a method includes determining a first region in a scene detected by a camera while the camera is in a first physical position. The method further includes receiving user input to target a sub-region within the first capture region of the scene and capturing the first image of the sub-region while the camera is in the first physical position. The first image is displayed in a fixed orientation on a preview portion of a display screen. The camera is moved to a second physical position and a second capture region of the scene is detected. The method further includes capturing a second image is of the sub-region and displaying it in the fixed orientation on the preview portion of the display screen. The second image is effective to inform a user of whether capture of the sub-region is altered by camera movement.

公开(公告)号：US11006122B2

公开(公告)日：2021-05-11

申请号：US16772069

申请日：2019-03-08

Applicant: Google LLC

Inventor： Wei Hong ,  Shengyi Lin

IPC: H04N5/232 ,  G06T7/20 ,  H04N19/137 ,  H04N19/30 ,  H04N19/513 ,  G06T3/40 ,  G06T5/00 ,  H04N19/176

Abstract: A computer-implemented method, system, or computer-readable medium may include estimating local motion of an input video frame of an input video by computing a local motion vector corresponding to a respective candidate pixel patch from among one or more candidate pixel patches within the input video frame. Global motion may be estimated by computing a global motion vector. One or more subject motion vectors may be computed based on a corresponding local motion vector and the global motion vector. A number of static frames of the video may be identified. The input video may be determined to be a static video if a ratio of the number of static frames to a number of the video frames in the input video meets a static frame threshold and determining that the input video is a motion video if the ratio fails to meet the static frame threshold.

公开(公告)号：US20200154053A1

公开(公告)日：2020-05-14

申请号：US16743795

申请日：2020-01-15

Applicant: Google LLC

Inventor： Radford Juang ,  Chia-Kai Liang ,  Wei Hong ,  Senpo Hu ,  Shengyi Lin ,  Erik Gross

IPC: H04N5/232

Abstract: Implementations generally relate to locking a camera onto a sub-region to capture images of the sub-region with a moving camera. In some implementations, a method includes determining a first region in a scene detected by a camera while the camera is in a first physical position. The method further includes receiving user input to target a sub-region within the first capture region of the scene and capturing the first image of the sub-region while the camera is in the first physical position. The first image is displayed in a fixed orientation on a preview portion of a display screen. The camera is moved to a second physical position and a second capture region of the scene is detected. The method further includes capturing a second image is of the sub-region and displaying it in the fixed orientation on the preview portion of the display screen. The second image is effective to inform a user of whether capture of the sub-region is altered by camera movement.

公开(公告)号：US11917158B2

公开(公告)日：2024-02-27

申请号：US17313799

申请日：2021-05-06

Applicant: Google LLC

Inventor： Wei Hong ,  Shengyi Lin

IPC: H04N7/12 ,  H04N19/137 ,  H04N19/176 ,  H04N19/30 ,  H04N19/513 ,  G06T3/40 ,  G06T5/00

CPC classification number: H04N19/137 ,  G06T3/40 ,  G06T5/002 ,  H04N19/176 ,  H04N19/30 ,  H04N19/521 ,  G06T2207/10016 ,  G06T2207/20076

Abstract: A computer-implemented method, system, or computer-readable medium may include estimating local motion of an input video frame of an input video by computing a local motion vector corresponding to a respective candidate pixel patch from among one or more candidate pixel patches within the input video frame. Global motion may be estimated by computing a global motion vector. One or more subject motion vectors may be computed based on a corresponding local motion vector and the global motion vector. A number of static frames of the video may be identified. The input video may be determined to be a static video if a ratio of the number of static frames to a number of the video frames in the input video meets a static frame threshold and determining that the input video is a motion video if the ratio fails to meet the static frame threshold.

公开(公告)号：US11102413B2

公开(公告)日：2021-08-24

申请号：US16743795

申请日：2020-01-15

Applicant: Google LLC

Inventor： Radford Juang ,  Chia-Kai Liang ,  Wei Hong ,  Senpo Hu ,  Shengyi Lin ,  Erik Gross

IPC: H04N5/232

Abstract: Implementations generally relate to locking a camera onto a sub-region to capture images of the sub-region with a moving camera. In some implementations, a method includes determining a first region in a scene detected by a camera while the camera is in a first physical position. The method further includes receiving user input to target a sub-region within the first capture region of the scene and capturing the first image of the sub-region while the camera is in the first physical position. The first image is displayed in a fixed orientation on a preview portion of a display screen. The camera is moved to a second physical position and a second capture region of the scene is detected. The method further includes capturing a second image is of the sub-region and displaying it in the fixed orientation on the preview portion of the display screen. The second image is effective to inform a user of whether capture of the sub-region is altered by camera movement.