Field variable tone mapping for 360 content

    公开(公告)号:US11758280B2

    公开(公告)日:2023-09-12

    申请号:US17749689

    申请日:2022-05-20

    Applicant: GoPro, Inc.

    CPC classification number: H04N23/741 G06T3/4038 G06T5/009 G06T5/20

    Abstract: Image capture devices and methods may use field variable tone mapping for 360 content. An image capture device may comprise an image sensor and a processor. The image sensor may capture a hyper-hemispherical image that includes an image circle portion. The processor may perform local tone mapping (LTM) on a first area of the image circle portion and perform global tone mapping (GTM) on a second area of pixels of the image circle portion. The GTM may be performed on a condition that a portion of a predefined area of pixels overlaps with a stitch line. The processor may be configured to stitch the hyper-hemispherical image and a second hyper-hemispherical image at the stitch line to obtain a processed image. The processor may be configured to display, store, output, or transmit the processed image.

    SCENE-BASED AUTOMATIC WHITE BALANCE

    公开(公告)号:US20230113349A1

    公开(公告)日:2023-04-13

    申请号:US18082027

    申请日:2022-12-15

    Applicant: GoPro, Inc.

    Abstract: Scene-based automatic white balance correction may be performed by obtaining an input image. A histogram may be computed from an image thumbnail. The scene-based automatic white balance correction may include classifying a scene. The scene-based automatic white balance correction may include learning a first filter and a second filter. The first filter and the second filter may be learned from one or several different instances of the raw image thumbnail, the augmented image thumbnail, the scene classification, or any combination thereof. The scene-based automatic white balance correction may include applying the filter to the histogram to determine white balance correction coefficients and obtain a processed image.

    COLOR FRINGING PROCESSING INDEPENDENT OF TONE MAPPING

    公开(公告)号:US20220021852A1

    公开(公告)日:2022-01-20

    申请号:US17299767

    申请日:2019-10-17

    Applicant: GoPro, Inc.

    Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor, detecting, in a linear domain, color fringing areas in the image, correcting detected color fringing areas to obtain a corrected image, performing tone mapping to the corrected image to obtain a tone mapped image and storing, displaying, or transmitting an output image based on at least the tone mapped image.

    NON-LINEAR COLOR CORRECTION
    4.
    发明申请

    公开(公告)号:US20200184690A1

    公开(公告)日:2020-06-11

    申请号:US16655944

    申请日:2019-10-17

    Applicant: GoPro, Inc.

    Abstract: Systems and methods are disclosed for non-linear color correction. The method including receiving an input image from an image sensor, converting the input image from a red, green, blue (RGB) color space format to an alternate color space format, determining localized hue correction parameters for a selected color in the alternate color space, determining localized saturation correction parameters for a selected hue in the alternate color space, applying the localized hue correction parameters and the localized saturation correction parameters to the input image to generate an output image and storing, displaying, or transmitting the output image based on at least the localized hue correction parameters and the localized saturation correction parameters.

    FIELD VARIABLE TONE MAPPING FOR 360 CONTENT

    公开(公告)号:US20220279109A1

    公开(公告)日:2022-09-01

    申请号:US17749689

    申请日:2022-05-20

    Applicant: GoPro, Inc.

    Abstract: Image capture devices and methods may use field variable tone mapping for 360 content. An image capture device may comprise an image sensor and a processor. The image sensor may capture a hyper-hemispherical image that includes an image circle portion. The processor may perform local tone mapping (LTM) on a first area of the image circle portion and perform global tone mapping (GTM) on a second area of pixels of the image circle portion. The GTM may be performed on a condition that a portion of a predefined area of pixels overlaps with a stitch line. The processor may be configured to stitch the hyper-hemispherical image and a second hyper-hemispherical image at the stitch line to obtain a processed image. The processor may be configured to display, store, output, or transmit the processed image.

    SCENE CLASSIFICATION FOR IMAGE PROCESSING
    6.
    发明申请

    公开(公告)号:US20190095713A1

    公开(公告)日:2019-03-28

    申请号:US16142608

    申请日:2018-09-26

    Applicant: GoPro, Inc.

    Abstract: Image analysis includes obtaining, from an image signal processor, image processing information corresponding to a previously processed image, obtaining scene classification information for an input image based on the image processing information, generating a processed image by processing the input image based on the scene classification information, and outputting the processed image. The image processing information includes automatic white balance correction information and obtaining the scene classification information includes obtaining the scene classification information based on the automatic white balance correction information.

    Scene-based automatic white balance

    公开(公告)号:US11558593B2

    公开(公告)日:2023-01-17

    申请号:US17171258

    申请日:2021-02-09

    Applicant: GoPro, Inc.

    Abstract: A method and apparatus may be used for performing a scene-based automatic white balance correction. The method may include obtaining an input image. The method may include obtaining a raw image thumbnail. The method may include obtaining an augmented image thumbnail. The method may include computing a histogram from an image thumbnail. The method may include determining a scene classification. The method may include learning a filter. The filter may be learned from one or several different instances of the raw image thumbnail, the augmented image thumbnail, the scene classification, or any combination thereof. The method may include applying the filter to the histogram to determine white balance correction coefficients and obtain a processed image.

    NON-LINEAR COLOR CORRECTION
    9.
    发明申请

    公开(公告)号:US20220020183A1

    公开(公告)日:2022-01-20

    申请号:US17490321

    申请日:2021-09-30

    Applicant: GoPro, Inc.

    Abstract: Systems and methods are disclosed for non-linear color correction. The method including receiving an input image from an image sensor, converting the input image from a red, green, blue (RGB) color space format to an alternate color space format, determining localized hue correction parameters for a selected color in the alternate color space, determining localized saturation correction parameters for a selected hue in the alternate color space, applying the localized hue correction parameters and the localized saturation correction parameters to the input image to generate an output image and storing, displaying, or transmitting the output image based on at least the localized hue correction parameters and the localized saturation correction parameters.

    SCENE-BASED AUTOMATIC WHITE BALANCE

    公开(公告)号:US20210250565A1

    公开(公告)日:2021-08-12

    申请号:US17171258

    申请日:2021-02-09

    Applicant: GoPro, Inc.

    Abstract: A method and apparatus may be used for performing a scene-based automatic white balance correction. The method may include obtaining an input image. The method may include obtaining a raw image thumbnail. The method may include obtaining an augmented image thumbnail. The method may include computing a histogram from an image thumbnail. The method may include determining a scene classification. The method may include learning a filter. The filter may be learned from one or several different instances of the raw image thumbnail, the augmented image thumbnail, the scene classification, or any combination thereof. The method may include applying the filter to the histogram to determine white balance correction coefficients and obtain a processed image.

Patent Agency Ranking