公开(公告)号：US12165063B2

公开(公告)日：2024-12-10

申请号：US18411445

申请日：2024-01-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yuqian Zhou ,  Timothy Andrew Large ,  Se Hoon Lim ,  Neil Emerton ,  Yonghuan David Ren

IPC: G06N3/08 ,  G06F18/214 ,  G06N20/00 ,  G06T5/50 ,  G06T5/70 ,  G06T5/73 ,  G06V10/44 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16 ,  H04N23/60

Abstract: Examples are disclosed that relate to the restoration of degraded images acquired via a behind-display camera. One example provides a method of training a machine learning model, the method comprising inputting training image pairs into the machine learning model, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, and training the machine learning model using the training image pairs to generate frequency information that is missing from the degraded images.

公开(公告)号：US11368617B2

公开(公告)日：2022-06-21

申请号：US16922266

申请日：2020-07-07

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yuqian Zhou ,  Timothy Andrew Large ,  Se Hoon Lim ,  Neil Emerton ,  Yonghuan David Ren

IPC: H04N5/232 ,  G06T5/50 ,  G06N20/00 ,  G06T5/00 ,  G06K9/62 ,  G06N3/08

Abstract: Examples are disclosed that relate to the restoration of degraded images acquired via a behind-display camera. One example provides a method of training a machine learning model, the method comprising inputting training image pairs into the machine learning model, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, and training the machine learning model using the training image pairs to generate frequency information that is missing from the degraded images.

公开(公告)号：US12125179B2

公开(公告)日：2024-10-22

申请号：US17755190

申请日：2020-11-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yonghuan David Ren ,  Timothy Andrew Large ,  Neil Emerton ,  Yuqian Zhou

IPC: G06T5/00 ,  G06T5/73 ,  H04N5/225 ,  H04N23/56

CPC classification number: G06T5/73 ,  H04N23/56 ,  G06T2207/20081

Abstract: An electronic device comprises a display, an illumination source, a camera, and a logic system. The illumination source is configured to project structured illumination onto a subject. The camera is configured to image the subject through the display, which includes collecting the structured illumination as reflected by the subject. The logic system is configured to receive, from the camera, a digital image of the subject imaged through the display. The logic system is further configured to sharpen the digital image based on the spatially resolved intensity of the structured illumination as reflected by the subject.

公开(公告)号：US11893482B2

公开(公告)日：2024-02-06

申请号：US16799597

申请日：2020-02-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yuqian Zhou ,  Timothy Andrew Large ,  Se Hoon Lim ,  Neil Emerton ,  Yonghuan David Ren

IPC: G06N3/08 ,  G06T5/50 ,  G06N20/00 ,  G06T5/00 ,  G06F18/214 ,  H04N23/60 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V10/44 ,  G06V40/16

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06N20/00 ,  G06T5/002 ,  G06T5/003 ,  G06T5/50 ,  G06V10/764 ,  G06V10/774 ,  H04N23/64 ,  G06V10/454 ,  G06V10/82 ,  G06V40/161

Abstract: Examples are disclosed that relate to the restoration of degraded images acquired via a behind-display camera. One example provides a method of training a machine learning model, the method comprising inputting training image pairs into the machine learning model, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, and training the machine learning model using the training image pairs to generate frequency information that is missing from the degraded images.

公开(公告)号：US20210144313A1

公开(公告)日：2021-05-13

申请号：US16679183

申请日：2019-11-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： Timothy A. Large ,  Neil Emerton ,  Yonghuan David Ren

IPC: H04N5/232 ,  H04N9/04 ,  H04N5/225

Abstract: Methods, systems and computer program products are provided for a logo camera. Camera thickness may be reduced using multiple lenses and sensors. A fixed or variable color icon may provide a function, notice or privacy warning, convey information, and/or serve decorative and/or other purposes. Color filters may be fixed or variable. A color icon may be created, for example, by controlling the colors of display pixels aligned with optical paths of camera lens and sensor arrays. Colors in an icon may provide color filters corresponding to an array of lenses that focus color-separated light on one or more camera sensors. Sensors may be optimized for particular colors. Color-separated images may be combined into a single image. Lens and camera sensor arrays may be compatible with multiple logos or other icon images. Cameras behind fixed or variable color icons may be concealed, for example, using shutters or semi-reflective layers.