METHOD FOR IMAGE PROCESSING USING LOCAL STATISTICS CONVOLUTION
    21.
    发明申请
    METHOD FOR IMAGE PROCESSING USING LOCAL STATISTICS CONVOLUTION 有权
    使用本地统计调查的图像处理方法

    公开(公告)号:US20160225126A1

    公开(公告)日:2016-08-04

    申请号:US15076404

    申请日:2016-03-21

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    Abstract: A method for filtering a digital image, comprising segmenting the digital image into a plurality of tiles; computing tile histograms corresponding to each of the plurality of tiles; deriving a plurality of tile transfer functions from the tile histograms preferably using 1D convolutions; interpolating a tile transfer function from the plurality of tile transfer functions; and filtering the digital image with the interpolated tile transfer function. Many filters otherwise difficult to conceive or to implement are possible with this method, including an edge-preserving smoothing filter, HDR tone mapping, edge invariant gradient or entropy detection, image upsampling, and mapping coarse data to fine data.

    Abstract translation: 一种用于过滤数字图像的方法,包括将所述数字图像分割成多个瓦片; 计算对应于所述多个瓦片中的每一个的瓦片直方图; 优选地使用1D卷积从所述瓦片直方图导出多个瓦片传送函数; 从所述多个瓦片传送功能内插瓦片传送功能; 并用内插的图块传递函数对数字图像进行滤波。 使用这种方法,可以使用许多滤波器来构思或实现,包括边缘保持平滑滤波器,HDR色调映射,边缘不变梯度或熵检测,图像上采样,以及将粗略数据映射到精细数据。

    DISTORTION OF DIGITAL IMAGES USING SPATIAL OFFSETS FROM IMAGE REFERENCE POINTS
    22.
    发明申请
    DISTORTION OF DIGITAL IMAGES USING SPATIAL OFFSETS FROM IMAGE REFERENCE POINTS 有权
    使用图像参考点的空间偏移对数字图像的失真

    公开(公告)号:US20150130831A1

    公开(公告)日:2015-05-14

    申请号:US14602296

    申请日:2015-01-22

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    Abstract: A method for distorting a digital image comprising receiving the coordinates of one or more than one image reference point defined by a user within the digital image, receiving one or more than one spatial offset assigned by the user and associated with the coordinates of the one or more than one defined image reference point, providing a mixing function algorithm embodied on a computer-readable medium for distorting the digital image, calculating an offset matrix by applying the mixing function algorithm based on the one or more than one spatial offset and the coordinates of the one or more than one defined image reference point; and distorting the digital image by application of the offset matrix. A graphic tag may be associated with each of the defined image reference points and displayed over the digital image, and the assignment of the spatial offset may be accomplished by movement of the graphic tag with the pointing device. Abstract image reference points may be used to limit distortion.

    Abstract translation: 一种用于使数字图像变形的方法,包括接收由数字图像内的用户定义的一个或多于一个图像参考点的坐标,接收由用户分配的一个或多于一个的空间偏移量, 多个定义的图像参考点,提供体现在计算机可读介质上的扭曲数字图像的混合函数算法,通过应用基于一个或多个空间偏移的混合函数算法和基于一个或多个空间偏移的坐标来计算偏移矩阵 一个或多个定义的图像参考点; 并通过应用偏移矩阵扭曲数字图像。 图形标签可以与每个定义的图像参考点相关联并且显示在数字图像上,并且空间偏移的分配可以通过图形标签与指示设备的移动来实现。 抽象图像参考点可用于限制失真。

    Compartmentalized image editing system

    公开(公告)号:US10331318B2

    公开(公告)日:2019-06-25

    申请号:US15066575

    申请日:2016-03-10

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    Abstract: Implementations generally relate to applying image enhancements. In some implementations, a method includes providing a selection of image enhancements to a user. The method also includes causing the image enhancements to be displayed as a collection of icons, where the collection includes icons representing different image enhancements, and where one or more of the image enhancements are applied to one or more images. The method also includes enabling the user to select any icon in the collection in order to modify the collection, where the selected icon has a corresponding selected image enhancement. The method also includes hiding icons associated with image enhancements that are subsequent image enhancements relative to the selected image enhancement. The method also includes deactivating the subsequent image enhancements corresponding to the hidden icons.

    Method for dynamic range editing
    26.
    发明授权
    Method for dynamic range editing 有权
    动态范围编辑方法

    公开(公告)号:US09589335B2

    公开(公告)日:2017-03-07

    申请号:US15051731

    申请日:2016-02-24

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    CPC classification number: G06T5/009 G06K9/36 G06K9/52 G06T2207/20208

    Abstract: A method of displaying a high dynamic range image, comprising receiving the high dynamic range image, calculating a first set of tone mapping parameters as a function of the high dynamic range image, sub-sampling the first set of tone mapping parameters at a first resolution to create a first sub-sampled parameter set, creating a first tone-mapped image by processing the high dynamic range image as a function of the first sub-sampled parameter set, and displaying the first tone-mapped image. A method of composting a plurality of versions of an image to create the high dynamic range image is also disclosed such that the compositing may be modified as a function of received user input.

    Abstract translation: 一种显示高动态范围图像的方法,包括接收高动态范围图像,计算作为高动态范围图像的函数的第一组色调映射参数,以第一分辨率对第一组色调映射参数进行二次采样 以创建第一子采样参数集,通过处理作为第一子采样参数集的函数的高动态范围图像来创建第一色调映射图像,并且显示第一色调映射图像。 还公开了堆叠图像的多个版本以创建高动态范围图像的方法,使得可以根据接收的用户输入来修改合成。

    Two-dimensional image processing based on third dimension data
    27.
    发明授权
    Two-dimensional image processing based on third dimension data 有权
    基于第三维数据的二维图像处理

    公开(公告)号:US09292906B1

    公开(公告)日:2016-03-22

    申请号:US14019808

    申请日:2013-09-06

    Applicant: Google Inc.

    Abstract: Systems, methods and computer readable media for two-dimensional image processing based on third dimension data are described. Some implementations can include a method comprising obtaining first image data having a plurality of pixel values and obtaining second image data corresponding to each pixel value in the first image data. The method can also include receiving an indication of one or more control points in the first image data. The method can further include selectively filtering the first image data based on a distance from the control point and on one or more data values in the second image data corresponding to the corresponding control point. The method can also include outputting the selectively filtered first image data.

    Abstract translation: 描述了基于第三维数据的用于二维图像处理的系统,方法和计算机可读介质。 一些实施方式可以包括一种方法,包括获得具有多个像素值的第一图像数据,并获得与第一图像数据中的每个像素值对应的第二图像数据。 该方法还可以包括接收第一图像数据中的一个或多个控制点的指示。 该方法还可以包括基于距控制点的距离以及对应于相应控制点的第二图像数据中的一个或多个数据值来选择性地过滤第一图像数据。 该方法还可以包括输出选择性滤波的第一图像数据。

    Method for dynamic range editing
    28.
    发明授权

    公开(公告)号:US09286665B2

    公开(公告)日:2016-03-15

    申请号:US14270313

    申请日:2014-05-05

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    CPC classification number: G06T5/009 G06K9/36 G06K9/52 G06T2207/20208

    Abstract: A method of displaying a high dynamic range image, comprising receiving the high dynamic range image, calculating a first set of tone mapping parameters as a function of the high dynamic range image, sub-sampling the first set of tone mapping parameters at a first resolution to create a first sub-sampled parameter set, creating a first tone-mapped image by processing the high dynamic range image as a function of the first sub-sampled parameter set, and displaying the first tone-mapped image. A method of composting a plurality of versions of an image to create the high dynamic range image is also disclosed such that the compositing may be modified as a function of received user input.

    Distortion of digital images using spatial offsets from image reference points
    29.
    发明授权
    Distortion of digital images using spatial offsets from image reference points 有权
    使用图像参考点的空间偏移的数字图像失真

    公开(公告)号:US09008420B2

    公开(公告)日:2015-04-14

    申请号:US14050312

    申请日:2013-10-09

    Applicant: Google Inc.

    Inventor: Nils Kokemohr

    Abstract: A method for distorting a digital image comprising receiving the coordinates of one or more than one image reference point defined by a user within the digital image, receiving one or more than one spatial offset assigned by the user and associated with the coordinates of the one or more than one defined image reference point, providing a mixing function algorithm embodied on a computer-readable medium for distorting the digital image, calculating an offset matrix by applying the mixing function algorithm based on the one or more than one spatial offset and the coordinates of the one or more than one defined image reference point; and distorting the digital image by application of the offset matrix. A graphic tag may be associated with each of the defined image reference points and displayed over the digital image, and the assignment of the spatial offset may be accomplished by movement of the graphic tag with the pointing device. Abstract image reference points may be used to limit distortion.

    Abstract translation: 一种用于使数字图像变形的方法,包括接收由数字图像内的用户定义的一个或多于一个图像参考点的坐标,接收由用户分配的一个或多于一个的空间偏移量, 多个定义的图像参考点,提供体现在计算机可读介质上的扭曲数字图像的混合函数算法,通过应用基于一个或多个空间偏移的混合函数算法和基于一个或多个空间偏移的坐标来计算偏移矩阵 一个或多个定义的图像参考点; 并通过应用偏移矩阵扭曲数字图像。 图形标签可以与每个定义的图像参考点相关联并且显示在数字图像上,并且空间偏移的分配可以通过图形标签与指示设备的移动来实现。 抽象图像参考点可用于限制失真。

    METHOD FOR DYNAMIC RANGE EDITING
    30.
    发明申请
    METHOD FOR DYNAMIC RANGE EDITING 有权
    动态范围编辑方法

    公开(公告)号:US20150010249A1

    公开(公告)日:2015-01-08

    申请号:US14270313

    申请日:2014-05-05

    Applicant: Google Inc

    Inventor: Nils Kokemohr

    CPC classification number: G06T5/009 G06K9/36 G06K9/52 G06T2207/20208

    Abstract: A method of displaying a high dynamic range image, comprising receiving the high dynamic range image, calculating a first set of tone mapping parameters as a function of the high dynamic range image, sub-sampling the first set of tone mapping parameters at a first resolution to create a first sub-sampled parameter set, creating a first tone-mapped image by processing the high dynamic range image as a function of the first sub-sampled parameter set, and displaying the first tone-mapped image. A method of composting a plurality of versions of an image to create the high dynamic range image is also disclosed such that the compositing may be modified as a function of received user input.

    Abstract translation: 一种显示高动态范围图像的方法,包括接收高动态范围图像,计算作为高动态范围图像的函数的第一组色调映射参数,以第一分辨率对第一组色调映射参数进行二次采样 以创建第一子采样参数集,通过处理作为第一子采样参数集的函数的高动态范围图像来创建第一色调映射图像,并且显示第一色调映射图像。 还公开了堆叠图像的多个版本以创建高动态范围图像的方法,使得可以根据接收的用户输入来修改合成。

Patent Agency Ranking